Name: Scicom-intl/Multilingual-TTS-Voice-Conversion
Creator: Scicom-intl
Published: 2026-03-15 02:03:23
License: 暂无描述

下载链接：

https://hf-mirror.com/datasets/Scicom-intl/Multilingual-TTS-Voice-Conversion

下载链接

链接失效反馈

官方服务：

资源简介：

--- dataset_info: - config_name: 9jalingo-hausa features: - name: reference_audio dtype: string - name: reference_text dtype: string - name: target_audio dtype: string - name: target_text dtype: string - name: source dtype: string splits: - name: train num_bytes: 1733068 num_examples: 5176 download_size: 286963 dataset_size: 1733068 - config_name: 9jalingo-yoruba features: - name: reference_audio dtype: string - name: reference_text dtype: string - name: target_audio dtype: string - name: target_text dtype: string - name: source dtype: string splits: - name: train num_bytes: 4876380 num_examples: 11676 download_size: 709982 dataset_size: 4876380 - config_name: AnimeVox features: - name: reference_audio dtype: string - name: reference_text dtype: string - name: target_audio dtype: string - name: target_text dtype: string - name: source dtype: string splits: - name: train num_bytes: 19726 num_examples: 46 download_size: 13503 dataset_size: 19726 - config_name: Arabic-Diacritized-TTS features: - name: reference_audio dtype: string - name: reference_text dtype: string - name: target_audio dtype: string - name: target_text dtype: string - name: source dtype: string splits: - name: train num_bytes: 274733465 num_examples: 250008 download_size: 20331135 dataset_size: 274733465 - config_name: Arabic_Diacritized_Audio_Dataset features: - name: reference_audio dtype: string - name: reference_text dtype: string - name: target_audio dtype: string - name: target_text dtype: string - name: source dtype: string splits: - name: train num_bytes: 73224238 num_examples: 100224 download_size: 1050720 dataset_size: 73224238 - config_name: Armenian-speech-corpus features: - name: reference_audio dtype: string - name: reference_text dtype: string - name: target_audio dtype: string - name: target_text dtype: string - name: source dtype: string splits: - name: train num_bytes: 43728098 num_examples: 125856 download_size: 3813536 dataset_size: 43728098 - config_name: Azerbaijani_News_TTS features: - name: reference_audio dtype: string - name: reference_text dtype: string - name: target_audio dtype: string - name: target_text dtype: string - name: source dtype: string splits: - name: train num_bytes: 72182257 num_examples: 100424 download_size: 29532471 dataset_size: 72182257 - config_name: Azure-TTS-Synthetic features: - name: reference_audio dtype: string - name: reference_text dtype: string - name: target_audio dtype: string - name: target_text dtype: string - name: source dtype: string splits: - name: train num_bytes: 4837276 num_examples: 18792 download_size: 99426 dataset_size: 4837276 - config_name: Azure-TTS-annotated features: - name: reference_audio dtype: string - name: reference_text dtype: string - name: target_audio dtype: string - name: target_text dtype: string - name: source dtype: string splits: - name: train num_bytes: 47082211 num_examples: 100000 download_size: 18088990 dataset_size: 47082211 - config_name: ClArTTS features: - name: reference_audio dtype: string - name: reference_text dtype: string - name: target_audio dtype: string - name: target_text dtype: string - name: source dtype: string splits: - name: train num_bytes: 24471191 num_examples: 50000 download_size: 1168564 dataset_size: 24471191 - config_name: CommonPhoneDataset features: - name: reference_audio dtype: string - name: reference_text dtype: string - name: target_audio dtype: string - name: target_text dtype: string - name: source dtype: string splits: - name: train num_bytes: 9788256 num_examples: 21638 download_size: 1330131 dataset_size: 9788256 - config_name: CommonVoice22_Sidon features: - name: reference_audio dtype: string - name: reference_text dtype: string - name: target_audio dtype: string - name: target_text dtype: string - name: source dtype: string splits: - name: train num_bytes: 289620814 num_examples: 680032 download_size: 59791571 dataset_size: 289620814 - config_name: Czech-Speech-Monospeaker-Honza features: - name: reference_audio dtype: string - name: reference_text dtype: string - name: target_audio dtype: string - name: target_text dtype: string - name: source dtype: string splits: - name: train num_bytes: 35026679 num_examples: 50036 download_size: 752797 dataset_size: 35026679 - config_name: DarijaTTS-clean features: - name: reference_audio dtype: string - name: reference_text dtype: string - name: target_audio dtype: string - name: target_text dtype: string - name: source dtype: string splits: - name: train num_bytes: 96668945 num_examples: 176270 download_size: 1499413 dataset_size: 96668945 - config_name: Dastum-yar-stt-breton-data features: - name: reference_audio dtype: string - name: reference_text dtype: string - name: target_audio dtype: string - name: target_text dtype: string - name: source dtype: string splits: - name: train num_bytes: 5802 num_examples: 22 download_size: 4790 dataset_size: 5802 - config_name: DisfluencySpeech features: - name: reference_audio dtype: string - name: reference_text dtype: string - name: target_audio dtype: string - name: target_text dtype: string - name: source dtype: string splits: - name: train num_bytes: 22937853 num_examples: 50000 download_size: 952881 dataset_size: 22937853 - config_name: Emilia-NV features: - name: reference_audio dtype: string - name: reference_text dtype: string - name: target_audio dtype: string - name: target_text dtype: string - name: source dtype: string splits: - name: train num_bytes: 590324954 num_examples: 987838 download_size: 134903567 dataset_size: 590324954 - config_name: GCP-TTS features: - name: reference_audio dtype: string - name: reference_text dtype: string - name: target_audio dtype: string - name: target_text dtype: string - name: source dtype: string splits: - name: train num_bytes: 64973167 num_examples: 200000 download_size: 30608356 dataset_size: 64973167 - config_name: GTTS-Chirp3-Synthetic features: - name: reference_audio dtype: string - name: reference_text dtype: string - name: target_audio dtype: string - name: target_text dtype: string - name: source dtype: string splits: - name: train num_bytes: 29458043 num_examples: 50000 download_size: 13189538 dataset_size: 29458043 - config_name: GTTS-WaveNet-Synthetic features: - name: reference_audio dtype: string - name: reference_text dtype: string - name: target_audio dtype: string - name: target_text dtype: string - name: source dtype: string splits: - name: train num_bytes: 120688069 num_examples: 200000 download_size: 32581685 dataset_size: 120688069 - config_name: Hellenic-greek-parliamentary-speech features: - name: reference_audio dtype: string - name: reference_text dtype: string - name: target_audio dtype: string - name: target_text dtype: string - name: source dtype: string splits: - name: train num_bytes: 34615006 num_examples: 46830 download_size: 2798502 dataset_size: 34615006 - config_name: Hindi-1482Hrs features: - name: reference_audio dtype: string - name: reference_text dtype: string - name: target_audio dtype: string - name: target_text dtype: string - name: source dtype: string splits: - name: train num_bytes: 2004750539 num_examples: 3360860 download_size: 215977428 dataset_size: 2004750539 - config_name: IMDA-TTS features: - name: reference_audio dtype: string - name: reference_text dtype: string - name: target_audio dtype: string - name: target_text dtype: string - name: source dtype: string splits: - name: train num_bytes: 13836241 num_examples: 50000 download_size: 747419 dataset_size: 13836241 - config_name: IndicTTS features: - name: reference_audio dtype: string - name: reference_text dtype: string - name: target_audio dtype: string - name: target_text dtype: string - name: source dtype: string splits: - name: train num_bytes: 365325721 num_examples: 417074 download_size: 101624058 dataset_size: 365325721 - config_name: IndicTTS_English features: - name: reference_audio dtype: string - name: reference_text dtype: string - name: target_audio dtype: string - name: target_text dtype: string - name: source dtype: string splits: - name: train num_bytes: 470339787 num_examples: 1177418 download_size: 24679202 dataset_size: 470339787 - config_name: IndicTTS_Telugu_MultiSpeaker features: - name: reference_audio dtype: string - name: reference_text dtype: string - name: target_audio dtype: string - name: target_text dtype: string - name: source dtype: string splits: - name: train num_bytes: 191544247 num_examples: 150050 download_size: 47427633 dataset_size: 191544247 - config_name: IndicTTS_v2 features: - name: reference_audio dtype: string - name: reference_text dtype: string - name: target_audio dtype: string - name: target_text dtype: string - name: source dtype: string splits: - name: train num_bytes: 459074877 num_examples: 626314 download_size: 105044989 dataset_size: 459074877 - config_name: Iqra_TTS features: - name: reference_audio dtype: string - name: reference_text dtype: string - name: target_audio dtype: string - name: target_text dtype: string - name: source dtype: string splits: - name: train num_bytes: 79153240 num_examples: 226028 download_size: 3336268 dataset_size: 79153240 - config_name: Japanese-Anime-Speech-v2 features: - name: reference_audio dtype: string - name: reference_text dtype: string - name: target_audio dtype: string - name: target_text dtype: string - name: source dtype: string splits: - name: train num_bytes: 280792613 num_examples: 558184 download_size: 20577704 dataset_size: 280792613 - config_name: MASC-Arabic features: - name: reference_audio dtype: string - name: reference_text dtype: string - name: target_audio dtype: string - name: target_text dtype: string - name: source dtype: string splits: - name: train num_bytes: 271029030 num_examples: 642752 download_size: 41102647 dataset_size: 271029030 - config_name: NepaliONE-tts features: - name: reference_audio dtype: string - name: reference_text dtype: string - name: target_audio dtype: string - name: target_text dtype: string - name: source dtype: string splits: - name: train num_bytes: 33437674 num_examples: 42890 download_size: 2555472 dataset_size: 33437674 - config_name: NonverbalTTS features: - name: reference_audio dtype: string - name: reference_text dtype: string - name: target_audio dtype: string - name: target_text dtype: string - name: source dtype: string splits: - name: train num_bytes: 594040 num_examples: 932 download_size: 163448 dataset_size: 594040 - config_name: NorthTTS_audio features: - name: reference_audio dtype: string - name: reference_text dtype: string - name: target_audio dtype: string - name: target_text dtype: string - name: source dtype: string splits: - name: train num_bytes: 8721204 num_examples: 7156 download_size: 165514 dataset_size: 8721204 - config_name: OpenSLR54-Nepali-ASR features: - name: reference_audio dtype: string - name: reference_text dtype: string - name: target_audio dtype: string - name: target_text dtype: string - name: source dtype: string splits: - name: train num_bytes: 976160 num_examples: 3038 download_size: 89094 dataset_size: 976160 - config_name: OutteTTS-urdu-dataset features: - name: reference_audio dtype: string - name: reference_text dtype: string - name: target_audio dtype: string - name: target_text dtype: string - name: source dtype: string splits: - name: train num_bytes: 28315901 num_examples: 50000 download_size: 1407050 dataset_size: 28315901 - config_name: Persian-Farsi-Speech features: - name: reference_audio dtype: string - name: reference_text dtype: string - name: target_audio dtype: string - name: target_text dtype: string - name: source dtype: string splits: - name: train num_bytes: 1059781683 num_examples: 937922 download_size: 203530334 dataset_size: 1059781683 - config_name: Persian_Course_TTS features: - name: reference_audio dtype: string - name: reference_text dtype: string - name: target_audio dtype: string - name: target_text dtype: string - name: source dtype: string splits: - name: train num_bytes: 616446 num_examples: 1084 download_size: 96017 dataset_size: 616446 - config_name: Porjai-Thai-voice-dataset-central features: - name: reference_audio dtype: string - name: reference_text dtype: string - name: target_audio dtype: string - name: target_text dtype: string - name: source dtype: string splits: - name: train num_bytes: 410660842 num_examples: 417272 download_size: 50734700 dataset_size: 410660842 - config_name: Porjai-Thai-voice-dataset-khummuang features: - name: reference_audio dtype: string - name: reference_text dtype: string - name: target_audio dtype: string - name: target_text dtype: string - name: source dtype: string splits: - name: train num_bytes: 14298572 num_examples: 21058 download_size: 427950 dataset_size: 14298572 - config_name: Porjai-Thai-voice-dataset-korat features: - name: reference_audio dtype: string - name: reference_text dtype: string - name: target_audio dtype: string - name: target_text dtype: string - name: source dtype: string splits: - name: train num_bytes: 4917572 num_examples: 8800 download_size: 158576 dataset_size: 4917572 - config_name: Porjai-Thai-voice-dataset-pattani features: - name: reference_audio dtype: string - name: reference_text dtype: string - name: target_audio dtype: string - name: target_text dtype: string - name: source dtype: string splits: - name: train num_bytes: 394428 num_examples: 778 download_size: 36400 dataset_size: 394428 - config_name: Punjabi_ASR_datasets features: - name: reference_audio dtype: string - name: reference_text dtype: string - name: target_audio dtype: string - name: target_text dtype: string - name: source dtype: string splits: - name: train num_bytes: 2525419658 num_examples: 1490022 download_size: 128237592 dataset_size: 2525419658 - config_name: SPRING_INX_Malayalam_R1 features: - name: reference_audio dtype: string - name: reference_text dtype: string - name: target_audio dtype: string - name: target_text dtype: string - name: source dtype: string splits: - name: train num_bytes: 700744342 num_examples: 629176 download_size: 53667336 dataset_size: 700744342 - config_name: SPRING_INX_Malayalam_R2 features: - name: reference_audio dtype: string - name: reference_text dtype: string - name: target_audio dtype: string - name: target_text dtype: string - name: source dtype: string splits: - name: train num_bytes: 296991546 num_examples: 261864 download_size: 28640707 dataset_size: 296991546 - config_name: StoryTTS features: - name: reference_audio dtype: string - name: reference_text dtype: string - name: target_audio dtype: string - name: target_text dtype: string - name: source dtype: string splits: - name: train num_bytes: 28571839 num_examples: 50000 download_size: 1539076 dataset_size: 28571839 - config_name: TTS-Danish features: - name: reference_audio dtype: string - name: reference_text dtype: string - name: target_audio dtype: string - name: target_text dtype: string - name: source dtype: string splits: - name: train num_bytes: 473933553 num_examples: 1015566 download_size: 41315351 dataset_size: 473933553 - config_name: TTS-Finnish features: - name: reference_audio dtype: string - name: reference_text dtype: string - name: target_audio dtype: string - name: target_text dtype: string - name: source dtype: string splits: - name: train num_bytes: 134089063 num_examples: 270148 download_size: 13223524 dataset_size: 134089063 - config_name: TTS-Greek features: - name: reference_audio dtype: string - name: reference_text dtype: string - name: target_audio dtype: string - name: target_text dtype: string - name: source dtype: string splits: - name: train num_bytes: 395673849 num_examples: 557248 download_size: 43821147 dataset_size: 395673849 - config_name: TTS-Hungarian features: - name: reference_audio dtype: string - name: reference_text dtype: string - name: target_audio dtype: string - name: target_text dtype: string - name: source dtype: string splits: - name: train num_bytes: 1157946434 num_examples: 2220390 download_size: 249720658 dataset_size: 1157946434 - config_name: TTS-Romanian features: - name: reference_audio dtype: string - name: reference_text dtype: string - name: target_audio dtype: string - name: target_text dtype: string - name: source dtype: string splits: - name: train num_bytes: 2460018448 num_examples: 4770138 download_size: 286138138 dataset_size: 2460018448 - config_name: TTS-Swedish features: - name: reference_audio dtype: string - name: reference_text dtype: string - name: target_audio dtype: string - name: target_text dtype: string - name: source dtype: string splits: - name: train num_bytes: 123812073 num_examples: 249074 download_size: 7232884 dataset_size: 123812073 - config_name: Tabaghe16_dataset_persian features: - name: reference_audio dtype: string - name: reference_text dtype: string - name: target_audio dtype: string - name: target_text dtype: string - name: source dtype: string splits: - name: train num_bytes: 77298136 num_examples: 157230 download_size: 9404673 dataset_size: 77298136 - config_name: Tamil_dataset_new features: - name: reference_audio dtype: string - name: reference_text dtype: string - name: target_audio dtype: string - name: target_text dtype: string - name: source dtype: string splits: - name: train num_bytes: 200178261 num_examples: 256660 download_size: 40786404 dataset_size: 200178261 - config_name: Telugu_ASR_corpus features: - name: reference_audio dtype: string - name: reference_text dtype: string - name: target_audio dtype: string - name: target_text dtype: string - name: source dtype: string splits: - name: train num_bytes: 43817494 num_examples: 47386 download_size: 874722 dataset_size: 43817494 - config_name: Thai-Voice-Test-10000 features: - name: reference_audio dtype: string - name: reference_text dtype: string - name: target_audio dtype: string - name: target_text dtype: string - name: source dtype: string splits: - name: train num_bytes: 3143542 num_examples: 5200 download_size: 324003 dataset_size: 3143542 - config_name: Thai-dialect-corpus features: - name: reference_audio dtype: string - name: reference_text dtype: string - name: target_audio dtype: string - name: target_text dtype: string - name: source dtype: string splits: - name: train num_bytes: 384315304 num_examples: 424890 download_size: 49539685 dataset_size: 384315304 - config_name: The_Spoken_Wikipedia_Corpora_Dutch_ASR_Hiidden features: - name: reference_audio dtype: string - name: reference_text dtype: string - name: target_audio dtype: string - name: target_text dtype: string - name: source dtype: string splits: - name: train num_bytes: 53469586 num_examples: 83038 download_size: 5089874 dataset_size: 53469586 - config_name: Turkish-Podcast-2 features: - name: reference_audio dtype: string - name: reference_text dtype: string - name: target_audio dtype: string - name: target_text dtype: string - name: source dtype: string splits: - name: train num_bytes: 28411964 num_examples: 50000 download_size: 10949904 dataset_size: 28411964 - config_name: Turkish_TTS_Data features: - name: reference_audio dtype: string - name: reference_text dtype: string - name: target_audio dtype: string - name: target_text dtype: string - name: source dtype: string splits: - name: train num_bytes: 51080426 num_examples: 100000 download_size: 13146456 dataset_size: 51080426 - config_name: UrduSpeech features: - name: reference_audio dtype: string - name: reference_text dtype: string - name: target_audio dtype: string - name: target_text dtype: string - name: source dtype: string splits: - name: train num_bytes: 158939164 num_examples: 244930 download_size: 46222464 dataset_size: 158939164 - config_name: UrduTTSDataset features: - name: reference_audio dtype: string - name: reference_text dtype: string - name: target_audio dtype: string - name: target_text dtype: string - name: source dtype: string splits: - name: train num_bytes: 382224 num_examples: 774 download_size: 62141 dataset_size: 382224 - config_name: UrduTTSDataset-22khz features: - name: reference_audio dtype: string - name: reference_text dtype: string - name: target_audio dtype: string - name: target_text dtype: string - name: source dtype: string splits: - name: train num_bytes: 405444 num_examples: 774 download_size: 63289 dataset_size: 405444 - config_name: VieNeu-TTS-140h features: - name: reference_audio dtype: string - name: reference_text dtype: string - name: target_audio dtype: string - name: target_text dtype: string - name: source dtype: string splits: - name: train num_bytes: 1808840202 num_examples: 3388448 download_size: 30795206 dataset_size: 1808840202 - config_name: VietSpeech features: - name: reference_audio dtype: string - name: reference_text dtype: string - name: target_audio dtype: string - name: target_text dtype: string - name: source dtype: string splits: - name: train num_bytes: 2637784698 num_examples: 6774288 download_size: 208746635 dataset_size: 2637784698 - config_name: WenetSpeech4TTS_Premium features: - name: reference_audio dtype: string - name: reference_text dtype: string - name: target_audio dtype: string - name: target_text dtype: string - name: source dtype: string splits: - name: train num_bytes: 745447323 num_examples: 1183336 download_size: 135437683 dataset_size: 745447323 - config_name: WolneLektury-TTS-Polish features: - name: reference_audio dtype: string - name: reference_text dtype: string - name: target_audio dtype: string - name: target_text dtype: string - name: source dtype: string splits: - name: train num_bytes: 3314018706 num_examples: 6143102 download_size: 457649665 dataset_size: 3314018706 - config_name: YodaLingua-Farsi features: - name: reference_audio dtype: string - name: reference_text dtype: string - name: target_audio dtype: string - name: target_text dtype: string - name: source dtype: string splits: - name: train num_bytes: 57908758 num_examples: 66882 download_size: 5171045 dataset_size: 57908758 - config_name: afrikaans-speech-dataset features: - name: reference_audio dtype: string - name: reference_text dtype: string - name: target_audio dtype: string - name: target_text dtype: string - name: source dtype: string splits: - name: train num_bytes: 18080924 num_examples: 34490 download_size: 519148 dataset_size: 18080924 - config_name: afrispeech_afrikaans features: - name: reference_audio dtype: string - name: reference_text dtype: string - name: target_audio dtype: string - name: target_text dtype: string - name: source dtype: string splits: - name: train num_bytes: 3472714 num_examples: 6886 download_size: 209021 dataset_size: 3472714 - config_name: amharic-speech features: - name: reference_audio dtype: string - name: reference_text dtype: string - name: target_audio dtype: string - name: target_text dtype: string - name: source dtype: string splits: - name: train num_bytes: 55232492 num_examples: 66782 download_size: 6073503 dataset_size: 55232492 - config_name: amharic_cleaned_testset_verified features: - name: reference_audio dtype: string - name: reference_text dtype: string - name: target_audio dtype: string - name: target_text dtype: string - name: source dtype: string splits: - name: train num_bytes: 377033847 num_examples: 519428 download_size: 52529419 dataset_size: 377033847 - config_name: anta_women_tts features: - name: reference_audio dtype: string - name: reference_text dtype: string - name: target_audio dtype: string - name: target_text dtype: string - name: source dtype: string splits: - name: train num_bytes: 23652 num_examples: 92 download_size: 9789 dataset_size: 23652 - config_name: armenian-speech-dataset features: - name: reference_audio dtype: string - name: reference_text dtype: string - name: target_audio dtype: string - name: target_text dtype: string - name: source dtype: string splits: - name: train num_bytes: 113976998 num_examples: 144568 download_size: 1524160 dataset_size: 113976998 - config_name: assamese-asr-dataset features: - name: reference_audio dtype: string - name: reference_text dtype: string - name: target_audio dtype: string - name: target_text dtype: string - name: source dtype: string splits: - name: train num_bytes: 482690557 num_examples: 558340 download_size: 69473056 dataset_size: 482690557 - config_name: assamese-tts-train features: - name: reference_audio dtype: string - name: reference_text dtype: string - name: target_audio dtype: string - name: target_text dtype: string - name: source dtype: string splits: - name: train num_bytes: 58831553 num_examples: 72876 download_size: 1043154 dataset_size: 58831553 - config_name: assamese_dataset features: - name: reference_audio dtype: string - name: reference_text dtype: string - name: target_audio dtype: string - name: target_text dtype: string - name: source dtype: string splits: - name: train num_bytes: 89223904 num_examples: 151648 download_size: 8091023 dataset_size: 89223904 - config_name: assamese_speech_corpus features: - name: reference_audio dtype: string - name: reference_text dtype: string - name: target_audio dtype: string - name: target_text dtype: string - name: source dtype: string splits: - name: train num_bytes: 70648398 num_examples: 101518 download_size: 7381720 dataset_size: 70648398 - config_name: assamese_speech_dataset1 features: - name: reference_audio dtype: string - name: reference_text dtype: string - name: target_audio dtype: string - name: target_text dtype: string - name: source dtype: string splits: - name: train num_bytes: 24056 num_examples: 58 download_size: 9727 dataset_size: 24056 - config_name: azerbaijani-audiobooks features: - name: reference_audio dtype: string - name: reference_text dtype: string - name: target_audio dtype: string - name: target_text dtype: string - name: source dtype: string splits: - name: train num_bytes: 31094143 num_examples: 50000 download_size: 8942625 dataset_size: 31094143 - config_name: azerbaijani-speech-dataset features: - name: reference_audio dtype: string - name: reference_text dtype: string - name: target_audio dtype: string - name: target_text dtype: string - name: source dtype: string splits: - name: train num_bytes: 486118056 num_examples: 882038 download_size: 53547435 dataset_size: 486118056 - config_name: azerbaijani-tts-dataset features: - name: reference_audio dtype: string - name: reference_text dtype: string - name: target_audio dtype: string - name: target_text dtype: string - name: source dtype: string splits: - name: train num_bytes: 48662 num_examples: 90 download_size: 24774 dataset_size: 48662 - config_name: basque_speech_dataset features: - name: reference_audio dtype: string - name: reference_text dtype: string - name: target_audio dtype: string - name: target_text dtype: string - name: source dtype: string splits: - name: train num_bytes: 43235342 num_examples: 121196 download_size: 992404 dataset_size: 43235342 - config_name: belarusian-speech-dataset features: - name: reference_audio dtype: string - name: reference_text dtype: string - name: target_audio dtype: string - name: target_text dtype: string - name: source dtype: string splits: - name: train num_bytes: 88540702 num_examples: 107934 download_size: 1196185 dataset_size: 88540702 - config_name: bplus_podcast_persian features: - name: reference_audio dtype: string - name: reference_text dtype: string - name: target_audio dtype: string - name: target_text dtype: string - name: source dtype: string splits: - name: train num_bytes: 161614 num_examples: 372 download_size: 47366 dataset_size: 161614 - config_name: bulgarian_tts features: - name: reference_audio dtype: string - name: reference_text dtype: string - name: target_audio dtype: string - name: target_text dtype: string - name: source dtype: string splits: - name: train num_bytes: 46896026 num_examples: 50528 download_size: 1195013 dataset_size: 46896026 - config_name: catalan-dataset features: - name: reference_audio dtype: string - name: reference_text dtype: string - name: target_audio dtype: string - name: target_text dtype: string - name: source dtype: string splits: - name: train num_bytes: 595248 num_examples: 1668 download_size: 106501 dataset_size: 595248 - config_name: catalan-speech-dataset features: - name: reference_audio dtype: string - name: reference_text dtype: string - name: target_audio dtype: string - name: target_text dtype: string - name: source dtype: string splits: - name: train num_bytes: 54680314 num_examples: 101862 download_size: 927005 dataset_size: 54680314 - config_name: clean_hausa_dataset features: - name: reference_audio dtype: string - name: reference_text dtype: string - name: target_audio dtype: string - name: target_text dtype: string - name: source dtype: string splits: - name: train num_bytes: 15938910 num_examples: 50000 download_size: 397131 dataset_size: 15938910 - config_name: clean_yoruba_dataset features: - name: reference_audio dtype: string - name: reference_text dtype: string - name: target_audio dtype: string - name: target_text dtype: string - name: source dtype: string splits: - name: train num_bytes: 814770 num_examples: 1832 download_size: 139846 dataset_size: 814770 - config_name: cml_tts_dataset_polish features: - name: reference_audio dtype: string - name: reference_text dtype: string - name: target_audio dtype: string - name: target_text dtype: string - name: source dtype: string splits: - name: train num_bytes: 106962862 num_examples: 179860 download_size: 27816277 dataset_size: 106962862 - config_name: cmu_haitian features: - name: reference_audio dtype: string - name: reference_text dtype: string - name: target_audio dtype: string - name: target_text dtype: string - name: source dtype: string splits: - name: train num_bytes: 13973578 num_examples: 39844 download_size: 654327 dataset_size: 13973578 - config_name: combined_amharic_speech_dataset features: - name: reference_audio dtype: string - name: reference_text dtype: string - name: target_audio dtype: string - name: target_text dtype: string - name: source dtype: string splits: - name: train num_bytes: 1484180293 num_examples: 2370138 download_size: 80903782 dataset_size: 1484180293 - config_name: combined_malayalam features: - name: reference_audio dtype: string - name: reference_text dtype: string - name: target_audio dtype: string - name: target_text dtype: string - name: source dtype: string splits: - name: train num_bytes: 417449978 num_examples: 574264 download_size: 44386460 dataset_size: 417449978 - config_name: czech_train_data features: - name: reference_audio dtype: string - name: reference_text dtype: string - name: target_audio dtype: string - name: target_text dtype: string - name: source dtype: string splits: - name: train num_bytes: 369836 num_examples: 946 download_size: 33369 dataset_size: 369836 - config_name: danish-speech-dataset features: - name: reference_audio dtype: string - name: reference_text dtype: string - name: target_audio dtype: string - name: target_text dtype: string - name: source dtype: string splits: - name: train num_bytes: 28456812 num_examples: 55976 download_size: 647459 dataset_size: 28456812 - config_name: dataset-vietvoice_v2 features: - name: reference_audio dtype: string - name: reference_text dtype: string - name: target_audio dtype: string - name: target_text dtype: string - name: source dtype: string splits: - name: train num_bytes: 88420524 num_examples: 180650 download_size: 24240604 dataset_size: 88420524 - config_name: egyptian-arabic-400k features: - name: reference_audio dtype: string - name: reference_text dtype: string - name: target_audio dtype: string - name: target_text dtype: string - name: source dtype: string splits: - name: train num_bytes: 213360413 num_examples: 633750 download_size: 34809798 dataset_size: 213360413 - config_name: elevenlabs_ru features: - name: reference_audio dtype: string - name: reference_text dtype: string - name: target_audio dtype: string - name: target_text dtype: string - name: source dtype: string splits: - name: train num_bytes: 239554990 num_examples: 296322 download_size: 3362125 dataset_size: 239554990 - config_name: estonian-speech-dataset features: - name: reference_audio dtype: string - name: reference_text dtype: string - name: target_audio dtype: string - name: target_text dtype: string - name: source dtype: string splits: - name: train num_bytes: 58664806 num_examples: 115994 download_size: 1017237 dataset_size: 58664806 - config_name: expresso features: - name: reference_audio dtype: string - name: reference_text dtype: string - name: target_audio dtype: string - name: target_text dtype: string - name: source dtype: string splits: - name: train num_bytes: 1092562 num_examples: 3436 download_size: 104006 dataset_size: 1092562 - config_name: filtered_nepali_male_dataset1 features: - name: reference_audio dtype: string - name: reference_text dtype: string - name: target_audio dtype: string - name: target_text dtype: string - name: source dtype: string splits: - name: train num_bytes: 48730809 num_examples: 50108 download_size: 12147367 dataset_size: 48730809 - config_name: galician-speech-dataset features: - name: reference_audio dtype: string - name: reference_text dtype: string - name: target_audio dtype: string - name: target_text dtype: string - name: source dtype: string splits: - name: train num_bytes: 120941782 num_examples: 227370 download_size: 1662245 dataset_size: 120941782 - config_name: gemini-flash-2.0-speech features: - name: reference_audio dtype: string - name: reference_text dtype: string - name: target_audio dtype: string - name: target_text dtype: string - name: source dtype: string splits: - name: train num_bytes: 78333138 num_examples: 100000 download_size: 38898839 dataset_size: 78333138 - config_name: genshin-voice features: - name: reference_audio dtype: string - name: reference_text dtype: string - name: target_audio dtype: string - name: target_text dtype: string - name: source dtype: string splits: - name: train num_bytes: 841884142 num_examples: 1678678 download_size: 114458588 dataset_size: 841884142 - config_name: google-colombian-spanish features: - name: reference_audio dtype: string - name: reference_text dtype: string - name: target_audio dtype: string - name: target_text dtype: string - name: source dtype: string splits: - name: train num_bytes: 4063696 num_examples: 10004 download_size: 197648 dataset_size: 4063696 - config_name: google_audio features: - name: reference_audio dtype: string - name: reference_text dtype: string - name: target_audio dtype: string - name: target_text dtype: string - name: source dtype: string splits: - name: train num_bytes: 78802582 num_examples: 137740 download_size: 3192288 dataset_size: 78802582 - config_name: greek-tts-dataset features: - name: reference_audio dtype: string - name: reference_text dtype: string - name: target_audio dtype: string - name: target_text dtype: string - name: source dtype: string splits: - name: train num_bytes: 21152872 num_examples: 30164 download_size: 538369 dataset_size: 21152872 - config_name: haqkiem-TTS features: - name: reference_audio dtype: string - name: reference_text dtype: string - name: target_audio dtype: string - name: target_text dtype: string - name: source dtype: string splits: - name: train num_bytes: 19160971 num_examples: 50000 download_size: 786474 dataset_size: 19160971 - config_name: hausa-tts-22k features: - name: reference_audio dtype: string - name: reference_text dtype: string - name: target_audio dtype: string - name: target_text dtype: string - name: source dtype: string splits: - name: train num_bytes: 16145698 num_examples: 49766 download_size: 2461429 dataset_size: 16145698 - config_name: hebrew-speech-dataset features: - name: reference_audio dtype: string - name: reference_text dtype: string - name: target_audio dtype: string - name: target_text dtype: string - name: source dtype: string splits: - name: train num_bytes: 45188122 num_examples: 73292 download_size: 847121 dataset_size: 45188122 - config_name: hebrew_speech_kan_nikud features: - name: reference_audio dtype: string - name: reference_text dtype: string - name: target_audio dtype: string - name: target_text dtype: string - name: source dtype: string splits: - name: train num_bytes: 15212 num_examples: 28 download_size: 9835 dataset_size: 15212 - config_name: hindi_ai4bharat_indictts features: - name: reference_audio dtype: string - name: reference_text dtype: string - name: target_audio dtype: string - name: target_text dtype: string - name: source dtype: string splits: - name: train num_bytes: 85507543 num_examples: 100126 download_size: 20841872 dataset_size: 85507543 - config_name: hindi_karya features: - name: reference_audio dtype: string - name: reference_text dtype: string - name: target_audio dtype: string - name: target_text dtype: string - name: source dtype: string splits: - name: train num_bytes: 69459032 num_examples: 160856 download_size: 2853624 dataset_size: 69459032 - config_name: hungarian-single-speaker-tts features: - name: reference_audio dtype: string - name: reference_text dtype: string - name: target_audio dtype: string - name: target_text dtype: string - name: source dtype: string splits: - name: train num_bytes: 27436585 num_examples: 50000 download_size: 1091286 dataset_size: 27436585 - config_name: hungarian-speech-dataset features: - name: reference_audio dtype: string - name: reference_text dtype: string - name: target_audio dtype: string - name: target_text dtype: string - name: source dtype: string splits: - name: train num_bytes: 48260006 num_examples: 86090 download_size: 914655 dataset_size: 48260006 - config_name: icelandic-speech-dataset features: - name: reference_audio dtype: string - name: reference_text dtype: string - name: target_audio dtype: string - name: target_text dtype: string - name: source dtype: string splits: - name: train num_bytes: 6505556 num_examples: 11998 download_size: 165475 dataset_size: 6505556 - config_name: indian_accent_english features: - name: reference_audio dtype: string - name: reference_text dtype: string - name: target_audio dtype: string - name: target_text dtype: string - name: source dtype: string splits: - name: train num_bytes: 20466243 num_examples: 50000 download_size: 934452 dataset_size: 20466243 - config_name: indic_hi_en_tts features: - name: reference_audio dtype: string - name: reference_text dtype: string - name: target_audio dtype: string - name: target_text dtype: string - name: source dtype: string splits: - name: train num_bytes: 48326023 num_examples: 100000 download_size: 12431781 dataset_size: 48326023 - config_name: indonesian-audiobook-tts features: - name: reference_audio dtype: string - name: reference_text dtype: string - name: target_audio dtype: string - name: target_text dtype: string - name: source dtype: string splits: - name: train num_bytes: 13779984 num_examples: 24166 download_size: 406241 dataset_size: 13779984 - config_name: japanese-anime-speech-v2 features: - name: reference_audio dtype: string - name: reference_text dtype: string - name: target_audio dtype: string - name: target_text dtype: string - name: source dtype: string splits: - name: train num_bytes: 255630510 num_examples: 499976 download_size: 23601362 dataset_size: 255630510 - config_name: jenny_tts_dataset features: - name: reference_audio dtype: string - name: reference_text dtype: string - name: target_audio dtype: string - name: target_text dtype: string - name: source dtype: string splits: - name: train num_bytes: 23331547 num_examples: 50000 download_size: 1736611 dataset_size: 23331547 - config_name: kazakh-emotional-tts features: - name: reference_audio dtype: string - name: reference_text dtype: string - name: target_audio dtype: string - name: target_text dtype: string - name: source dtype: string splits: - name: train num_bytes: 43020950 num_examples: 63532 download_size: 6853938 dataset_size: 43020950 - config_name: kazakh-speech-dataset features: - name: reference_audio dtype: string - name: reference_text dtype: string - name: target_audio dtype: string - name: target_text dtype: string - name: source dtype: string splits: - name: train num_bytes: 73092422 num_examples: 98136 download_size: 1136119 dataset_size: 73092422 - config_name: kazakh-stt features: - name: reference_audio dtype: string - name: reference_text dtype: string - name: target_audio dtype: string - name: target_text dtype: string - name: source dtype: string splits: - name: train num_bytes: 4558345534 num_examples: 7224710 download_size: 82326023 dataset_size: 4558345534 - config_name: kazakh-tts-test features: - name: reference_audio dtype: string - name: reference_text dtype: string - name: target_audio dtype: string - name: target_text dtype: string - name: source dtype: string splits: - name: train num_bytes: 118334566 num_examples: 180398 download_size: 12155083 dataset_size: 118334566 - config_name: kazakh-tts-val features: - name: reference_audio dtype: string - name: reference_text dtype: string - name: target_audio dtype: string - name: target_text dtype: string - name: source dtype: string splits: - name: train num_bytes: 115768862 num_examples: 178530 download_size: 11992239 dataset_size: 115768862 - config_name: kazakh_speech_dataset_ksd features: - name: reference_audio dtype: string - name: reference_text dtype: string - name: target_audio dtype: string - name: target_text dtype: string - name: source dtype: string splits: - name: train num_bytes: 3474126002 num_examples: 4905392 download_size: 161854629 dataset_size: 3474126002 - config_name: kazakh_speech_mfa_punctuation features: - name: reference_audio dtype: string - name: reference_text dtype: string - name: target_audio dtype: string - name: target_text dtype: string - name: source dtype: string splits: - name: train num_bytes: 1253064655 num_examples: 1750942 download_size: 241785929 dataset_size: 1253064655 - config_name: khanacademy-turkish-math features: - name: reference_audio dtype: string - name: reference_text dtype: string - name: target_audio dtype: string - name: target_text dtype: string - name: source dtype: string splits: - name: train num_bytes: 101770753 num_examples: 142094 download_size: 34828045 dataset_size: 101770753 - config_name: kinyarwanda-tts-dataset features: - name: reference_audio dtype: string - name: reference_text dtype: string - name: target_audio dtype: string - name: target_text dtype: string - name: source dtype: string splits: - name: train num_bytes: 12884040 num_examples: 33484 download_size: 556203 dataset_size: 12884040 - config_name: lao-asr-thesis-dataset features: - name: reference_audio dtype: string - name: reference_text dtype: string - name: target_audio dtype: string - name: target_text dtype: string - name: source dtype: string splits: - name: train num_bytes: 266724532 num_examples: 313612 download_size: 3155538 dataset_size: 266724532 - config_name: lao-data-speech features: - name: reference_audio dtype: string - name: reference_text dtype: string - name: target_audio dtype: string - name: target_text dtype: string - name: source dtype: string splits: - name: train num_bytes: 263647151 num_examples: 318680 download_size: 3181467 dataset_size: 263647151 - config_name: lao-speech-dataset features: - name: reference_audio dtype: string - name: reference_text dtype: string - name: target_audio dtype: string - name: target_text dtype: string - name: source dtype: string splits: - name: train num_bytes: 275060658 num_examples: 325362 download_size: 3365652 dataset_size: 275060658 - config_name: laos-speech-dataset features: - name: reference_audio dtype: string - name: reference_text dtype: string - name: target_audio dtype: string - name: target_text dtype: string - name: source dtype: string splits: - name: train num_bytes: 379940530 num_examples: 455262 download_size: 4464909 dataset_size: 379940530 - config_name: laos-voice-dataset-v2 features: - name: reference_audio dtype: string - name: reference_text dtype: string - name: target_audio dtype: string - name: target_text dtype: string - name: source dtype: string splits: - name: train num_bytes: 450822967 num_examples: 523026 download_size: 5288459 dataset_size: 450822967 - config_name: latvian-speech-dataset features: - name: reference_audio dtype: string - name: reference_text dtype: string - name: target_audio dtype: string - name: target_text dtype: string - name: source dtype: string splits: - name: train num_bytes: 66796094 num_examples: 128704 download_size: 1012012 dataset_size: 66796094 - config_name: lithuanian-speech-dataset features: - name: reference_audio dtype: string - name: reference_text dtype: string - name: target_audio dtype: string - name: target_text dtype: string - name: source dtype: string splits: - name: train num_bytes: 69705416 num_examples: 131296 download_size: 1163716 dataset_size: 69705416 - config_name: macedonian features: - name: reference_audio dtype: string - name: reference_text dtype: string - name: target_audio dtype: string - name: target_text dtype: string - name: source dtype: string splits: - name: train num_bytes: 138227970 num_examples: 137650 download_size: 36300460 dataset_size: 138227970 - config_name: macedonian-speech-dataset features: - name: reference_audio dtype: string - name: reference_text dtype: string - name: target_audio dtype: string - name: target_text dtype: string - name: source dtype: string splits: - name: train num_bytes: 74944918 num_examples: 97614 download_size: 1012492 dataset_size: 74944918 - config_name: malay-audiobook features: - name: reference_audio dtype: string - name: reference_text dtype: string - name: target_audio dtype: string - name: target_text dtype: string - name: source dtype: string splits: - name: train num_bytes: 79491062 num_examples: 150000 download_size: 15959391 dataset_size: 79491062 - config_name: malayalam-speech-dataset features: - name: reference_audio dtype: string - name: reference_text dtype: string - name: target_audio dtype: string - name: target_text dtype: string - name: source dtype: string splits: - name: train num_bytes: 1011569223 num_examples: 1000146 download_size: 126695487 dataset_size: 1011569223 - config_name: malayalam-whisper-corpus_v3 features: - name: reference_audio dtype: string - name: reference_text dtype: string - name: target_audio dtype: string - name: target_text dtype: string - name: source dtype: string splits: - name: train num_bytes: 119484801 num_examples: 155536 download_size: 5270336 dataset_size: 119484801 - config_name: malayalam_data_from_bhashini_100125 features: - name: reference_audio dtype: string - name: reference_text dtype: string - name: target_audio dtype: string - name: target_text dtype: string - name: source dtype: string splits: - name: train num_bytes: 383145914 num_examples: 353192 download_size: 53194553 dataset_size: 383145914 - config_name: malayalam_dataset_17_01_25 features: - name: reference_audio dtype: string - name: reference_text dtype: string - name: target_audio dtype: string - name: target_text dtype: string - name: source dtype: string splits: - name: train num_bytes: 133650691 num_examples: 208224 download_size: 12449238 dataset_size: 133650691 - config_name: maltese-speech-dataset features: - name: reference_audio dtype: string - name: reference_text dtype: string - name: target_audio dtype: string - name: target_text dtype: string - name: source dtype: string splits: - name: train num_bytes: 89192252 num_examples: 170182 download_size: 1370639 dataset_size: 89192252 - config_name: marathi-speech-dataset features: - name: reference_audio dtype: string - name: reference_text dtype: string - name: target_audio dtype: string - name: target_text dtype: string - name: source dtype: string splits: - name: train num_bytes: 4961799948 num_examples: 4872848 download_size: 641973480 dataset_size: 4961799948 - config_name: marathi_asr_dataset features: - name: reference_audio dtype: string - name: reference_text dtype: string - name: target_audio dtype: string - name: target_text dtype: string - name: source dtype: string splits: - name: train num_bytes: 17652094 num_examples: 35594 download_size: 493247 dataset_size: 17652094 - config_name: marathi_reg_test_set features: - name: reference_audio dtype: string - name: reference_text dtype: string - name: target_audio dtype: string - name: target_text dtype: string - name: source dtype: string splits: - name: train num_bytes: 173100 num_examples: 148 download_size: 46077 dataset_size: 173100 - config_name: maya-audio features: - name: reference_audio dtype: string - name: reference_text dtype: string - name: target_audio dtype: string - name: target_text dtype: string - name: source dtype: string splits: - name: train num_bytes: 947180 num_examples: 2078 download_size: 61228 dataset_size: 947180 - config_name: merged_Arabic-Diacritized_ClArTTS features: - name: reference_audio dtype: string - name: reference_text dtype: string - name: target_audio dtype: string - name: target_text dtype: string - name: source dtype: string splits: - name: train num_bytes: 316637670 num_examples: 306560 download_size: 50883207 dataset_size: 316637670 - config_name: merged_urdu_TTS features: - name: reference_audio dtype: string - name: reference_text dtype: string - name: target_audio dtype: string - name: target_text dtype: string - name: source dtype: string splits: - name: train num_bytes: 45150956 num_examples: 91836 download_size: 5455559 dataset_size: 45150956 - config_name: mgb2-arabic features: - name: reference_audio dtype: string - name: reference_text dtype: string - name: target_audio dtype: string - name: target_text dtype: string - name: source dtype: string splits: - name: train num_bytes: 1846678811 num_examples: 2399852 download_size: 274102076 dataset_size: 1846678811 - config_name: multilingual-tts features: - name: reference_audio dtype: string - name: reference_text dtype: string - name: target_audio dtype: string - name: target_text dtype: string - name: source dtype: string splits: - name: train num_bytes: 64505094 num_examples: 122294 download_size: 1401882 dataset_size: 64505094 - config_name: nepali-slr features: - name: reference_audio dtype: string - name: reference_text dtype: string - name: target_audio dtype: string - name: target_text dtype: string - name: source dtype: string splits: - name: train num_bytes: 294893978 num_examples: 812528 download_size: 3900604 dataset_size: 294893978 - config_name: nepali_speech_to_text features: - name: reference_audio dtype: string - name: reference_text dtype: string - name: target_audio dtype: string - name: target_text dtype: string - name: source dtype: string splits: - name: train num_bytes: 209441496 num_examples: 226162 download_size: 2744136 dataset_size: 209441496 - config_name: norwegian-100h features: - name: reference_audio dtype: string - name: reference_text dtype: string - name: target_audio dtype: string - name: target_text dtype: string - name: source dtype: string splits: - name: train num_bytes: 9547518 num_examples: 25556 download_size: 1155703 dataset_size: 9547518 - config_name: norwegian-100h-v2 features: - name: reference_audio dtype: string - name: reference_text dtype: string - name: target_audio dtype: string - name: target_text dtype: string - name: source dtype: string splits: - name: train num_bytes: 105874404 num_examples: 177484 download_size: 11443683 dataset_size: 105874404 - config_name: norwegian-100h-v3 features: - name: reference_audio dtype: string - name: reference_text dtype: string - name: target_audio dtype: string - name: target_text dtype: string - name: source dtype: string splits: - name: train num_bytes: 120895914 num_examples: 202900 download_size: 13042651 dataset_size: 120895914 - config_name: norwegian-nynorsk-speech-dataset features: - name: reference_audio dtype: string - name: reference_text dtype: string - name: target_audio dtype: string - name: target_text dtype: string - name: source dtype: string splits: - name: train num_bytes: 101474312 num_examples: 186818 download_size: 1428284 dataset_size: 101474312 - config_name: occitan-speech-dataset features: - name: reference_audio dtype: string - name: reference_text dtype: string - name: target_audio dtype: string - name: target_text dtype: string - name: source dtype: string splits: - name: train num_bytes: 31989232 num_examples: 59436 download_size: 788791 dataset_size: 31989232 - config_name: openslr-140-hq-Kazakh features: - name: reference_audio dtype: string - name: reference_text dtype: string - name: target_audio dtype: string - name: target_text dtype: string - name: source dtype: string splits: - name: train num_bytes: 3426527203 num_examples: 5030174 download_size: 130793943 dataset_size: 3426527203 - config_name: opentts-lada features: - name: reference_audio dtype: string - name: reference_text dtype: string - name: target_audio dtype: string - name: target_text dtype: string - name: source dtype: string splits: - name: train num_bytes: 16448508 num_examples: 38664 download_size: 519129 dataset_size: 16448508 - config_name: original_data_malayalam_tts features: - name: reference_audio dtype: string - name: reference_text dtype: string - name: target_audio dtype: string - name: target_text dtype: string - name: source dtype: string splits: - name: train num_bytes: 111470858 num_examples: 145580 download_size: 3984117 dataset_size: 111470858 - config_name: punjabi-asr features: - name: reference_audio dtype: string - name: reference_text dtype: string - name: target_audio dtype: string - name: target_text dtype: string - name: source dtype: string splits: - name: train num_bytes: 390895838 num_examples: 376342 download_size: 91843551 dataset_size: 390895838 - config_name: ru_book_dataset features: - name: reference_audio dtype: string - name: reference_text dtype: string - name: target_audio dtype: string - name: target_text dtype: string - name: source dtype: string splits: - name: train num_bytes: 137230566 num_examples: 200000 download_size: 24884423 dataset_size: 137230566 - config_name: serbian-speech-dataset features: - name: reference_audio dtype: string - name: reference_text dtype: string - name: target_audio dtype: string - name: target_text dtype: string - name: source dtype: string splits: - name: train num_bytes: 97391401 num_examples: 185740 download_size: 1444581 dataset_size: 97391401 - config_name: singaporean_accent_district_names_continuation features: - name: reference_audio dtype: string - name: reference_text dtype: string - name: target_audio dtype: string - name: target_text dtype: string - name: source dtype: string splits: - name: train num_bytes: 6275422 num_examples: 12314 download_size: 171967 dataset_size: 6275422 - config_name: slovak-speech-dataset features: - name: reference_audio dtype: string - name: reference_text dtype: string - name: target_audio dtype: string - name: target_text dtype: string - name: source dtype: string splits: - name: train num_bytes: 39053640 num_examples: 76878 download_size: 777896 dataset_size: 39053640 - config_name: slovenian-speech-dataset features: - name: reference_audio dtype: string - name: reference_text dtype: string - name: target_audio dtype: string - name: target_text dtype: string - name: source dtype: string splits: - name: train num_bytes: 37736282 num_examples: 73626 download_size: 796553 dataset_size: 37736282 - config_name: somali-tts-datasets features: - name: reference_audio dtype: string - name: reference_text dtype: string - name: target_audio dtype: string - name: target_text dtype: string - name: source dtype: string splits: - name: train num_bytes: 247138 num_examples: 628 download_size: 32806 dataset_size: 247138 - config_name: swahili-speech-400hr features: - name: reference_audio dtype: string - name: reference_text dtype: string - name: target_audio dtype: string - name: target_text dtype: string - name: source dtype: string splits: - name: train num_bytes: 1083001883 num_examples: 1546064 download_size: 84206227 dataset_size: 1083001883 - config_name: swahili_asr_data features: - name: reference_audio dtype: string - name: reference_text dtype: string - name: target_audio dtype: string - name: target_text dtype: string - name: source dtype: string splits: - name: train num_bytes: 4419966 num_examples: 12026 download_size: 629584 dataset_size: 4419966 - config_name: syspin-telugu-tts features: - name: reference_audio dtype: string - name: reference_text dtype: string - name: target_audio dtype: string - name: target_text dtype: string - name: source dtype: string splits: - name: train num_bytes: 44869415 num_examples: 50000 download_size: 16272629 dataset_size: 44869415 - config_name: tajik-asr-augmented-test features: - name: reference_audio dtype: string - name: reference_text dtype: string - name: target_audio dtype: string - name: target_text dtype: string - name: source dtype: string splits: - name: train num_bytes: 748624 num_examples: 1004 download_size: 48080 dataset_size: 748624 - config_name: tajik-speech-dataset features: - name: reference_audio dtype: string - name: reference_text dtype: string - name: target_audio dtype: string - name: target_text dtype: string - name: source dtype: string splits: - name: train num_bytes: 65369530 num_examples: 88530 download_size: 1010365 dataset_size: 65369530 - config_name: tamil-speech-dataset features: - name: reference_audio dtype: string - name: reference_text dtype: string - name: target_audio dtype: string - name: target_text dtype: string - name: source dtype: string splits: - name: train num_bytes: 2808030563 num_examples: 2504592 download_size: 507540904 dataset_size: 2808030563 - config_name: telugu-asr features: - name: reference_audio dtype: string - name: reference_text dtype: string - name: target_audio dtype: string - name: target_text dtype: string - name: source dtype: string splits: - name: train num_bytes: 1401786793 num_examples: 1481946 download_size: 238071393 dataset_size: 1401786793 - config_name: telugu_OpenSLR features: - name: reference_audio dtype: string - name: reference_text dtype: string - name: target_audio dtype: string - name: target_text dtype: string - name: source dtype: string splits: - name: train num_bytes: 1058038 num_examples: 2368 download_size: 102138 dataset_size: 1058038 - config_name: telugu_tts features: - name: reference_audio dtype: string - name: reference_text dtype: string - name: target_audio dtype: string - name: target_text dtype: string - name: source dtype: string splits: - name: train num_bytes: 1010678 num_examples: 2368 download_size: 99224 dataset_size: 1010678 - config_name: telugu_whisper_asr features: - name: reference_audio dtype: string - name: reference_text dtype: string - name: target_audio dtype: string - name: target_text dtype: string - name: source dtype: string splits: - name: train num_bytes: 889486 num_examples: 1876 download_size: 92054 dataset_size: 889486 - config_name: thai-audio-full-trainval features: - name: reference_audio dtype: string - name: reference_text dtype: string - name: target_audio dtype: string - name: target_text dtype: string - name: source dtype: string splits: - name: train num_bytes: 49114604 num_examples: 96266 download_size: 5021289 dataset_size: 49114604 - config_name: tibetan_wz_tts features: - name: reference_audio dtype: string - name: reference_text dtype: string - name: target_audio dtype: string - name: target_text dtype: string - name: source dtype: string splits: - name: train num_bytes: 8873742 num_examples: 6892 download_size: 363580 dataset_size: 8873742 - config_name: tts-indo features: - name: reference_audio dtype: string - name: reference_text dtype: string - name: target_audio dtype: string - name: target_text dtype: string - name: source dtype: string splits: - name: train num_bytes: 7101106 num_examples: 24888 download_size: 429170 dataset_size: 7101106 - config_name: turkish_female features: - name: reference_audio dtype: string - name: reference_text dtype: string - name: target_audio dtype: string - name: target_text dtype: string - name: source dtype: string splits: - name: train num_bytes: 28548434 num_examples: 50000 download_size: 1654465 dataset_size: 28548434 - config_name: turkish_male features: - name: reference_audio dtype: string - name: reference_text dtype: string - name: target_audio dtype: string - name: target_text dtype: string - name: source dtype: string splits: - name: train num_bytes: 20681816 num_examples: 50028 download_size: 8298904 dataset_size: 20681816 - config_name: turkmen-speech features: - name: reference_audio dtype: string - name: reference_text dtype: string - name: target_audio dtype: string - name: target_text dtype: string - name: source dtype: string splits: - name: train num_bytes: 517055005 num_examples: 825350 download_size: 110694457 dataset_size: 517055005 - config_name: ukrainian-speech-dataset features: - name: reference_audio dtype: string - name: reference_text dtype: string - name: target_audio dtype: string - name: target_text dtype: string - name: source dtype: string splits: - name: train num_bytes: 124612669 num_examples: 168324 download_size: 1775596 dataset_size: 124612669 - config_name: urdu-tts-speaker3 features: - name: reference_audio dtype: string - name: reference_text dtype: string - name: target_audio dtype: string - name: target_text dtype: string - name: source dtype: string splits: - name: train num_bytes: 38440697 num_examples: 50000 download_size: 11802484 dataset_size: 38440697 - config_name: urdu-voice-dataset features: - name: reference_audio dtype: string - name: reference_text dtype: string - name: target_audio dtype: string - name: target_text dtype: string - name: source dtype: string splits: - name: train num_bytes: 72078 num_examples: 174 download_size: 23724 dataset_size: 72078 - config_name: uzbek-speech-corpus features: - name: reference_audio dtype: string - name: reference_text dtype: string - name: target_audio dtype: string - name: target_text dtype: string - name: source dtype: string splits: - name: train num_bytes: 18613032 num_examples: 53630 download_size: 2303096 dataset_size: 18613032 - config_name: uzbekvoice features: - name: reference_audio dtype: string - name: reference_text dtype: string - name: target_audio dtype: string - name: target_text dtype: string - name: source dtype: string splits: - name: train num_bytes: 249795430 num_examples: 827728 download_size: 43414484 dataset_size: 249795430 - config_name: uzbekvoice-2k-each-accent features: - name: reference_audio dtype: string - name: reference_text dtype: string - name: target_audio dtype: string - name: target_text dtype: string - name: source dtype: string splits: - name: train num_bytes: 300522 num_examples: 906 download_size: 53061 dataset_size: 300522 - config_name: waxal-tts features: - name: reference_audio dtype: string - name: reference_text dtype: string - name: target_audio dtype: string - name: target_text dtype: string - name: source dtype: string splits: - name: train num_bytes: 19288434 num_examples: 37126 download_size: 799905 dataset_size: 19288434 - config_name: welsh-speech-dataset features: - name: reference_audio dtype: string - name: reference_text dtype: string - name: target_audio dtype: string - name: target_text dtype: string - name: source dtype: string splits: - name: train num_bytes: 56369766 num_examples: 111832 download_size: 1047778 dataset_size: 56369766 - config_name: yoruba-speech-text-parallel features: - name: reference_audio dtype: string - name: reference_text dtype: string - name: target_audio dtype: string - name: target_text dtype: string - name: source dtype: string splits: - name: train num_bytes: 46092476 num_examples: 78436 download_size: 2291603 dataset_size: 46092476 - config_name: zh-yue-tts-dataset features: - name: reference_audio dtype: string - name: reference_text dtype: string - name: target_audio dtype: string - name: target_text dtype: string - name: source dtype: string splits: - name: train num_bytes: 18559394 num_examples: 50000 download_size: 6982336 dataset_size: 18559394 configs: - config_name: 9jalingo-hausa data_files: - split: train path: 9jalingo-hausa/train-* - config_name: 9jalingo-yoruba data_files: - split: train path: 9jalingo-yoruba/train-* - config_name: AnimeVox data_files: - split: train path: AnimeVox/train-* - config_name: Arabic-Diacritized-TTS data_files: - split: train path: Arabic-Diacritized-TTS/train-* - config_name: Arabic_Diacritized_Audio_Dataset data_files: - split: train path: Arabic_Diacritized_Audio_Dataset/train-* - config_name: Armenian-speech-corpus data_files: - split: train path: Armenian-speech-corpus/train-* - config_name: Azerbaijani_News_TTS data_files: - split: train path: Azerbaijani_News_TTS/train-* - config_name: Azure-TTS-Synthetic data_files: - split: train path: Azure-TTS-Synthetic/train-* - config_name: Azure-TTS-annotated data_files: - split: train path: Azure-TTS-annotated/train-* - config_name: ClArTTS data_files: - split: train path: ClArTTS/train-* - config_name: CommonPhoneDataset data_files: - split: train path: CommonPhoneDataset/train-* - config_name: CommonVoice22_Sidon data_files: - split: train path: CommonVoice22_Sidon/train-* - config_name: Czech-Speech-Monospeaker-Honza data_files: - split: train path: Czech-Speech-Monospeaker-Honza/train-* - config_name: DarijaTTS-clean data_files: - split: train path: DarijaTTS-clean/train-* - config_name: Dastum-yar-stt-breton-data data_files: - split: train path: Dastum-yar-stt-breton-data/train-* - config_name: DisfluencySpeech data_files: - split: train path: DisfluencySpeech/train-* - config_name: Emilia-NV data_files: - split: train path: Emilia-NV/train-* - config_name: GCP-TTS data_files: - split: train path: GCP-TTS/train-* - config_name: GTTS-Chirp3-Synthetic data_files: - split: train path: GTTS-Chirp3-Synthetic/train-* - config_name: GTTS-WaveNet-Synthetic data_files: - split: train path: GTTS-WaveNet-Synthetic/train-* - config_name: Hellenic-greek-parliamentary-speech data_files: - split: train path: Hellenic-greek-parliamentary-speech/train-* - config_name: Hindi-1482Hrs data_files: - split: train path: Hindi-1482Hrs/train-* - config_name: IMDA-TTS data_files: - split: train path: IMDA-TTS/train-* - config_name: IndicTTS data_files: - split: train path: IndicTTS/train-* - config_name: IndicTTS_English data_files: - split: train path: IndicTTS_English/train-* - config_name: IndicTTS_Telugu_MultiSpeaker data_files: - split: train path: IndicTTS_Telugu_MultiSpeaker/train-* - config_name: IndicTTS_v2 data_files: - split: train path: IndicTTS_v2/train-* - config_name: Iqra_TTS data_files: - split: train path: Iqra_TTS/train-* - config_name: Japanese-Anime-Speech-v2 data_files: - split: train path: Japanese-Anime-Speech-v2/train-* - config_name: MASC-Arabic data_files: - split: train path: MASC-Arabic/train-* - config_name: NepaliONE-tts data_files: - split: train path: NepaliONE-tts/train-* - config_name: NonverbalTTS data_files: - split: train path: NonverbalTTS/train-* - config_name: NorthTTS_audio data_files: - split: train path: NorthTTS_audio/train-* - config_name: OpenSLR54-Nepali-ASR data_files: - split: train path: OpenSLR54-Nepali-ASR/train-* - config_name: OutteTTS-urdu-dataset data_files: - split: train path: OutteTTS-urdu-dataset/train-* - config_name: Persian-Farsi-Speech data_files: - split: train path: Persian-Farsi-Speech/train-* - config_name: Persian_Course_TTS data_files: - split: train path: Persian_Course_TTS/train-* - config_name: Porjai-Thai-voice-dataset-central data_files: - split: train path: Porjai-Thai-voice-dataset-central/train-* - config_name: Porjai-Thai-voice-dataset-khummuang data_files: - split: train path: Porjai-Thai-voice-dataset-khummuang/train-* - config_name: Porjai-Thai-voice-dataset-korat data_files: - split: train path: Porjai-Thai-voice-dataset-korat/train-* - config_name: Porjai-Thai-voice-dataset-pattani data_files: - split: train path: Porjai-Thai-voice-dataset-pattani/train-* - config_name: Punjabi_ASR_datasets data_files: - split: train path: Punjabi_ASR_datasets/train-* - config_name: SPRING_INX_Malayalam_R1 data_files: - split: train path: SPRING_INX_Malayalam_R1/train-* - config_name: SPRING_INX_Malayalam_R2 data_files: - split: train path: SPRING_INX_Malayalam_R2/train-* - config_name: StoryTTS data_files: - split: train path: StoryTTS/train-* - config_name: TTS-Danish data_files: - split: train path: TTS-Danish/train-* - config_name: TTS-Finnish data_files: - split: train path: TTS-Finnish/train-* - config_name: TTS-Greek data_files: - split: train path: TTS-Greek/train-* - config_name: TTS-Hungarian data_files: - split: train path: TTS-Hungarian/train-* - config_name: TTS-Romanian data_files: - split: train path: TTS-Romanian/train-* - config_name: TTS-Swedish data_files: - split: train path: TTS-Swedish/train-* - config_name: Tabaghe16_dataset_persian data_files: - split: train path: Tabaghe16_dataset_persian/train-* - config_name: Tamil_dataset_new data_files: - split: train path: Tamil_dataset_new/train-* - config_name: Telugu_ASR_corpus data_files: - split: train path: Telugu_ASR_corpus/train-* - config_name: Thai-Voice-Test-10000 data_files: - split: train path: Thai-Voice-Test-10000/train-* - config_name: Thai-dialect-corpus data_files: - split: train path: Thai-dialect-corpus/train-* - config_name: The_Spoken_Wikipedia_Corpora_Dutch_ASR_Hiidden data_files: - split: train path: The_Spoken_Wikipedia_Corpora_Dutch_ASR_Hiidden/train-* - config_name: Turkish-Podcast-2 data_files: - split: train path: Turkish-Podcast-2/train-* - config_name: Turkish_TTS_Data data_files: - split: train path: Turkish_TTS_Data/train-* - config_name: UrduSpeech data_files: - split: train path: UrduSpeech/train-* - config_name: UrduTTSDataset data_files: - split: train path: UrduTTSDataset/train-* - config_name: UrduTTSDataset-22khz data_files: - split: train path: UrduTTSDataset-22khz/train-* - config_name: VieNeu-TTS-140h data_files: - split: train path: VieNeu-TTS-140h/train-* - config_name: VietSpeech data_files: - split: train path: VietSpeech/train-* - config_name: WenetSpeech4TTS_Premium data_files: - split: train path: WenetSpeech4TTS_Premium/train-* - config_name: WolneLektury-TTS-Polish data_files: - split: train path: WolneLektury-TTS-Polish/train-* - config_name: YodaLingua-Farsi data_files: - split: train path: YodaLingua-Farsi/train-* - config_name: afrikaans-speech-dataset data_files: - split: train path: afrikaans-speech-dataset/train-* - config_name: afrispeech_afrikaans data_files: - split: train path: afrispeech_afrikaans/train-* - config_name: amharic-speech data_files: - split: train path: amharic-speech/train-* - config_name: amharic_cleaned_testset_verified data_files: - split: train path: amharic_cleaned_testset_verified/train-* - config_name: anta_women_tts data_files: - split: train path: anta_women_tts/train-* - config_name: armenian-speech-dataset data_files: - split: train path: armenian-speech-dataset/train-* - config_name: assamese-asr-dataset data_files: - split: train path: assamese-asr-dataset/train-* - config_name: assamese-tts-train data_files: - split: train path: assamese-tts-train/train-* - config_name: assamese_dataset data_files: - split: train path: assamese_dataset/train-* - config_name: assamese_speech_corpus data_files: - split: train path: assamese_speech_corpus/train-* - config_name: assamese_speech_dataset1 data_files: - split: train path: assamese_speech_dataset1/train-* - config_name: azerbaijani-audiobooks data_files: - split: train path: azerbaijani-audiobooks/train-* - config_name: azerbaijani-speech-dataset data_files: - split: train path: azerbaijani-speech-dataset/train-* - config_name: azerbaijani-tts-dataset data_files: - split: train path: azerbaijani-tts-dataset/train-* - config_name: basque_speech_dataset data_files: - split: train path: basque_speech_dataset/train-* - config_name: belarusian-speech-dataset data_files: - split: train path: belarusian-speech-dataset/train-* - config_name: bplus_podcast_persian data_files: - split: train path: bplus_podcast_persian/train-* - config_name: bulgarian_tts data_files: - split: train path: bulgarian_tts/train-* - config_name: catalan-dataset data_files: - split: train path: catalan-dataset/train-* - config_name: catalan-speech-dataset data_files: - split: train path: catalan-speech-dataset/train-* - config_name: clean_hausa_dataset data_files: - split: train path: clean_hausa_dataset/train-* - config_name: clean_yoruba_dataset data_files: - split: train path: clean_yoruba_dataset/train-* - config_name: cml_tts_dataset_polish data_files: - split: train path: cml_tts_dataset_polish/train-* - config_name: cmu_haitian data_files: - split: train path: cmu_haitian/train-* - config_name: combined_amharic_speech_dataset data_files: - split: train path: combined_amharic_speech_dataset/train-* - config_name: combined_malayalam data_files: - split: train path: combined_malayalam/train-* - config_name: czech_train_data data_files: - split: train path: czech_train_data/train-* - config_name: danish-speech-dataset data_files: - split: train path: danish-speech-dataset/train-* - config_name: dataset-vietvoice_v2 data_files: - split: train path: dataset-vietvoice_v2/train-* - config_name: egyptian-arabic-400k data_files: - split: train path: egyptian-arabic-400k/train-* - config_name: elevenlabs_ru data_files: - split: train path: elevenlabs_ru/train-* - config_name: estonian-speech-dataset data_files: - split: train path: estonian-speech-dataset/train-* - config_name: expresso data_files: - split: train path: expresso/train-* - config_name: filtered_nepali_male_dataset1 data_files: - split: train path: filtered_nepali_male_dataset1/train-* - config_name: galician-speech-dataset data_files: - split: train path: galician-speech-dataset/train-* - config_name: gemini-flash-2.0-speech data_files: - split: train path: gemini-flash-2.0-speech/train-* - config_name: genshin-voice data_files: - split: train path: genshin-voice/train-* - config_name: google-colombian-spanish data_files: - split: train path: google-colombian-spanish/train-* - config_name: google_audio data_files: - split: train path: google_audio/train-* - config_name: greek-tts-dataset data_files: - split: train path: greek-tts-dataset/train-* - config_name: haqkiem-TTS data_files: - split: train path: haqkiem-TTS/train-* - config_name: hausa-tts-22k data_files: - split: train path: hausa-tts-22k/train-* - config_name: hebrew-speech-dataset data_files: - split: train path: hebrew-speech-dataset/train-* - config_name: hebrew_speech_kan_nikud data_files: - split: train path: hebrew_speech_kan_nikud/train-* - config_name: hindi_ai4bharat_indictts data_files: - split: train path: hindi_ai4bharat_indictts/train-* - config_name: hindi_karya data_files: - split: train path: hindi_karya/train-* - config_name: hungarian-single-speaker-tts data_files: - split: train path: hungarian-single-speaker-tts/train-* - config_name: hungarian-speech-dataset data_files: - split: train path: hungarian-speech-dataset/train-* - config_name: icelandic-speech-dataset data_files: - split: train path: icelandic-speech-dataset/train-* - config_name: indian_accent_english data_files: - split: train path: indian_accent_english/train-* - config_name: indic_hi_en_tts data_files: - split: train path: indic_hi_en_tts/train-* - config_name: indonesian-audiobook-tts data_files: - split: train path: indonesian-audiobook-tts/train-* - config_name: japanese-anime-speech-v2 data_files: - split: train path: japanese-anime-speech-v2/train-* - config_name: jenny_tts_dataset data_files: - split: train path: jenny_tts_dataset/train-* - config_name: kazakh-emotional-tts data_files: - split: train path: kazakh-emotional-tts/train-* - config_name: kazakh-speech-dataset data_files: - split: train path: kazakh-speech-dataset/train-* - config_name: kazakh-stt data_files: - split: train path: kazakh-stt/train-* - config_name: kazakh-tts-test data_files: - split: train path: kazakh-tts-test/train-* - config_name: kazakh-tts-val data_files: - split: train path: kazakh-tts-val/train-* - config_name: kazakh_speech_dataset_ksd data_files: - split: train path: kazakh_speech_dataset_ksd/train-* - config_name: kazakh_speech_mfa_punctuation data_files: - split: train path: kazakh_speech_mfa_punctuation/train-* - config_name: khanacademy-turkish-math data_files: - split: train path: khanacademy-turkish-math/train-* - config_name: kinyarwanda-tts-dataset data_files: - split: train path: kinyarwanda-tts-dataset/train-* - config_name: lao-asr-thesis-dataset data_files: - split: train path: lao-asr-thesis-dataset/train-* - config_name: lao-data-speech data_files: - split: train path: lao-data-speech/train-* - config_name: lao-speech-dataset data_files: - split: train path: lao-speech-dataset/train-* - config_name: laos-speech-dataset data_files: - split: train path: laos-speech-dataset/train-* - config_name: laos-voice-dataset-v2 data_files: - split: train path: laos-voice-dataset-v2/train-* - config_name: latvian-speech-dataset data_files: - split: train path: latvian-speech-dataset/train-* - config_name: lithuanian-speech-dataset data_files: - split: train path: lithuanian-speech-dataset/train-* - config_name: macedonian data_files: - split: train path: macedonian/train-* - config_name: macedonian-speech-dataset data_files: - split: train path: macedonian-speech-dataset/train-* - config_name: malay-audiobook data_files: - split: train path: malay-audiobook/train-* - config_name: malayalam-speech-dataset data_files: - split: train path: malayalam-speech-dataset/train-* - config_name: malayalam-whisper-corpus_v3 data_files: - split: train path: malayalam-whisper-corpus_v3/train-* - config_name: malayalam_data_from_bhashini_100125 data_files: - split: train path: malayalam_data_from_bhashini_100125/train-* - config_name: malayalam_dataset_17_01_25 data_files: - split: train path: malayalam_dataset_17_01_25/train-* - config_name: maltese-speech-dataset data_files: - split: train path: maltese-speech-dataset/train-* - config_name: marathi-speech-dataset data_files: - split: train path: marathi-speech-dataset/train-* - config_name: marathi_asr_dataset data_files: - split: train path: marathi_asr_dataset/train-* - config_name: marathi_reg_test_set data_files: - split: train path: marathi_reg_test_set/train-* - config_name: maya-audio data_files: - split: train path: maya-audio/train-* - config_name: merged_Arabic-Diacritized_ClArTTS data_files: - split: train path: merged_Arabic-Diacritized_ClArTTS/train-* - config_name: merged_urdu_TTS data_files: - split: train path: merged_urdu_TTS/train-* - config_name: mgb2-arabic data_files: - split: train path: mgb2-arabic/train-* - config_name: multilingual-tts data_files: - split: train path: multilingual-tts/train-* - config_name: nepali-slr data_files: - split: train path: nepali-slr/train-* - config_name: nepali_speech_to_text data_files: - split: train path: nepali_speech_to_text/train-* - config_name: norwegian-100h data_files: - split: train path: norwegian-100h/train-* - config_name: norwegian-100h-v2 data_files: - split: train path: norwegian-100h-v2/train-* - config_name: norwegian-100h-v3 data_files: - split: train path: norwegian-100h-v3/train-* - config_name: norwegian-nynorsk-speech-dataset data_files: - split: train path: norwegian-nynorsk-speech-dataset/train-* - config_name: occitan-speech-dataset data_files: - split: train path: occitan-speech-dataset/train-* - config_name: openslr-140-hq-Kazakh data_files: - split: train path: openslr-140-hq-Kazakh/train-* - config_name: opentts-lada data_files: - split: train path: opentts-lada/train-* - config_name: original_data_malayalam_tts data_files: - split: train path: original_data_malayalam_tts/train-* - config_name: punjabi-asr data_files: - split: train path: punjabi-asr/train-* - config_name: ru_book_dataset data_files: - split: train path: ru_book_dataset/train-* - config_name: serbian-speech-dataset data_files: - split: train path: serbian-speech-dataset/train-* - config_name: singaporean_accent_district_names_continuation data_files: - split: train path: singaporean_accent_district_names_continuation/train-* - config_name: slovak-speech-dataset data_files: - split: train path: slovak-speech-dataset/train-* - config_name: slovenian-speech-dataset data_files: - split: train path: slovenian-speech-dataset/train-* - config_name: somali-tts-datasets data_files: - split: train path: somali-tts-datasets/train-* - config_name: swahili-speech-400hr data_files: - split: train path: swahili-speech-400hr/train-* - config_name: swahili_asr_data data_files: - split: train path: swahili_asr_data/train-* - config_name: syspin-telugu-tts data_files: - split: train path: syspin-telugu-tts/train-* - config_name: tajik-asr-augmented-test data_files: - split: train path: tajik-asr-augmented-test/train-* - config_name: tajik-speech-dataset data_files: - split: train path: tajik-speech-dataset/train-* - config_name: tamil-speech-dataset data_files: - split: train path: tamil-speech-dataset/train-* - config_name: telugu-asr data_files: - split: train path: telugu-asr/train-* - config_name: telugu_OpenSLR data_files: - split: train path: telugu_OpenSLR/train-* - config_name: telugu_tts data_files: - split: train path: telugu_tts/train-* - config_name: telugu_whisper_asr data_files: - split: train path: telugu_whisper_asr/train-* - config_name: thai-audio-full-trainval data_files: - split: train path: thai-audio-full-trainval/train-* - config_name: tibetan_wz_tts data_files: - split: train path: tibetan_wz_tts/train-* - config_name: tts-indo data_files: - split: train path: tts-indo/train-* - config_name: turkish_female data_files: - split: train path: turkish_female/train-* - config_name: turkish_male data_files: - split: train path: turkish_male/train-* - config_name: turkmen-speech data_files: - split: train path: turkmen-speech/train-* - config_name: ukrainian-speech-dataset data_files: - split: train path: ukrainian-speech-dataset/train-* - config_name: urdu-tts-speaker3 data_files: - split: train path: urdu-tts-speaker3/train-* - config_name: urdu-voice-dataset data_files: - split: train path: urdu-voice-dataset/train-* - config_name: uzbek-speech-corpus data_files: - split: train path: uzbek-speech-corpus/train-* - config_name: uzbekvoice data_files: - split: train path: uzbekvoice/train-* - config_name: uzbekvoice-2k-each-accent data_files: - split: train path: uzbekvoice-2k-each-accent/train-* - config_name: waxal-tts data_files: - split: train path: waxal-tts/train-* - config_name: welsh-speech-dataset data_files: - split: train path: welsh-speech-dataset/train-* - config_name: yoruba-speech-text-parallel data_files: - split: train path: yoruba-speech-text-parallel/train-* - config_name: zh-yue-tts-dataset data_files: - split: train path: zh-yue-tts-dataset/train-* --- # Multilingual-TTS-Voice-Conversion Convert TTS dataset to become Voice Conversion dataset by doing similarity combination. Multilingual TTS comes from [malaysia-ai/Multilingual-TTS](https://huggingface.co/datasets/malaysia-ai/Multilingual-TTS) ## Source code Source code at https://github.com/Scicom-AI-Enterprise-Organization/Multilingual-TTS/tree/main/vc-tts ## Acknowledgement Special thanks to https://www.scitix.ai/ for H100 Node!

应用场景：