Name: SpeechPPL/SALMon_pGSLM-normalized2
Creator: SpeechPPL
Published: 2026-04-10 13:52:03
License: 暂无描述

下载链接：

https://hf-mirror.com/datasets/SpeechPPL/SALMon_pGSLM-normalized2

下载链接

链接失效反馈

官方服务：

资源简介：

--- dataset_info: - config_name: bg_alignment features: - name: task dtype: string - name: ind dtype: int64 - name: positive_sample_tokenwise_loss list: float32 - name: negative_sample_tokenwise_loss list: float32 - name: prompt_sample_tokenwise_loss list: float32 - name: model_generated_continuation dtype: audio: sampling_rate: 16000 - name: positive_audio dtype: audio: sampling_rate: 16000 - name: negative_audio dtype: audio: sampling_rate: 16000 - name: positive_sample_raw_units dtype: - name: hubert dtype: string - name: negative_sample_raw_units dtype: - name: hubert dtype: string - name: prompt_audio dtype: audio: sampling_rate: 16000 - name: code_frame_rate dtype: int64 - name: code_depth dtype: int64 - name: model_sampling_rate dtype: int64 - name: ppl_sanity dtype: int64 - name: positive_continuation_tokenwise_loss dtype: 'null' - name: negative_continuation_tokenwise_loss dtype: 'null' - name: positive_continuation_raw_units dtype: - name: hubert dtype: string - name: negative_continuation_raw_units dtype: - name: hubert dtype: string - name: continuation_audio_positive dtype: audio: sampling_rate: 16000 - name: continuation_audio_negative dtype: audio: sampling_rate: 16000 splits: - name: train num_bytes: 87019899 num_examples: 200 download_size: 87019899 dataset_size: 87019899 - config_name: bg_all_consistency features: - name: task dtype: string - name: ind dtype: int64 - name: positive_sample_tokenwise_loss list: float32 - name: negative_sample_tokenwise_loss list: float32 - name: prompt_sample_tokenwise_loss list: float32 - name: model_generated_continuation dtype: audio: sampling_rate: 16000 - name: positive_audio dtype: audio: sampling_rate: 16000 - name: negative_audio dtype: audio: sampling_rate: 16000 - name: positive_sample_raw_units dtype: - name: hubert dtype: string - name: negative_sample_raw_units dtype: - name: hubert dtype: string - name: prompt_audio dtype: audio: sampling_rate: 16000 - name: code_frame_rate dtype: int64 - name: code_depth dtype: int64 - name: model_sampling_rate dtype: int64 - name: ppl_sanity dtype: int64 - name: positive_continuation_tokenwise_loss list: float64 - name: negative_continuation_tokenwise_loss list: float64 - name: positive_continuation_raw_units dtype: - name: hubert dtype: string - name: negative_continuation_raw_units dtype: - name: hubert dtype: string - name: continuation_audio_positive dtype: audio: sampling_rate: 16000 - name: continuation_audio_negative dtype: audio: sampling_rate: 16000 splits: - name: train num_bytes: 207143109 num_examples: 200 download_size: 207143109 dataset_size: 207143109 - config_name: bg_domain_consistency features: - name: task dtype: string - name: ind dtype: int64 - name: positive_sample_tokenwise_loss list: float32 - name: negative_sample_tokenwise_loss list: float32 - name: prompt_sample_tokenwise_loss list: float32 - name: model_generated_continuation dtype: audio: sampling_rate: 16000 - name: positive_audio dtype: audio: sampling_rate: 16000 - name: negative_audio dtype: audio: sampling_rate: 16000 - name: positive_sample_raw_units dtype: - name: hubert dtype: string - name: negative_sample_raw_units dtype: - name: hubert dtype: string - name: prompt_audio dtype: audio: sampling_rate: 16000 - name: code_frame_rate dtype: int64 - name: code_depth dtype: int64 - name: model_sampling_rate dtype: int64 - name: ppl_sanity dtype: int64 - name: positive_continuation_tokenwise_loss list: float64 - name: negative_continuation_tokenwise_loss list: float64 - name: positive_continuation_raw_units dtype: - name: hubert dtype: string - name: negative_continuation_raw_units dtype: - name: hubert dtype: string - name: continuation_audio_positive dtype: audio: sampling_rate: 16000 - name: continuation_audio_negative dtype: audio: sampling_rate: 16000 splits: - name: train num_bytes: 210303767 num_examples: 200 download_size: 210303767 dataset_size: 210303767 - config_name: gender_consistency features: - name: task dtype: string - name: ind dtype: int64 - name: positive_sample_tokenwise_loss list: float32 - name: negative_sample_tokenwise_loss list: float32 - name: prompt_sample_tokenwise_loss list: float32 - name: model_generated_continuation dtype: audio: sampling_rate: 16000 - name: positive_audio dtype: audio: sampling_rate: 16000 - name: negative_audio dtype: audio: sampling_rate: 16000 - name: positive_sample_raw_units dtype: - name: hubert dtype: string - name: negative_sample_raw_units dtype: - name: hubert dtype: string - name: prompt_audio dtype: audio: sampling_rate: 16000 - name: code_frame_rate dtype: int64 - name: code_depth dtype: int64 - name: model_sampling_rate dtype: int64 - name: ppl_sanity dtype: int64 - name: positive_continuation_tokenwise_loss list: float64 - name: negative_continuation_tokenwise_loss list: float64 - name: positive_continuation_raw_units dtype: - name: hubert dtype: string - name: negative_continuation_raw_units dtype: - name: hubert dtype: string - name: continuation_audio_positive dtype: audio: sampling_rate: 16000 - name: continuation_audio_negative dtype: audio: sampling_rate: 16000 splits: - name: train num_bytes: 209062383 num_examples: 200 download_size: 209062383 dataset_size: 209062383 - config_name: rir_consistency features: - name: task dtype: string - name: ind dtype: int64 - name: positive_sample_tokenwise_loss list: float32 - name: negative_sample_tokenwise_loss list: float32 - name: prompt_sample_tokenwise_loss list: float32 - name: model_generated_continuation dtype: audio: sampling_rate: 16000 - name: positive_audio dtype: audio: sampling_rate: 16000 - name: negative_audio dtype: audio: sampling_rate: 16000 - name: positive_sample_raw_units dtype: - name: hubert dtype: string - name: negative_sample_raw_units dtype: - name: hubert dtype: string - name: prompt_audio dtype: audio: sampling_rate: 16000 - name: code_frame_rate dtype: int64 - name: code_depth dtype: int64 - name: model_sampling_rate dtype: int64 - name: ppl_sanity dtype: int64 - name: positive_continuation_tokenwise_loss list: float64 - name: negative_continuation_tokenwise_loss list: float64 - name: positive_continuation_raw_units dtype: - name: hubert dtype: string - name: negative_continuation_raw_units dtype: - name: hubert dtype: string - name: continuation_audio_positive dtype: audio: sampling_rate: 16000 - name: continuation_audio_negative dtype: audio: sampling_rate: 16000 splits: - name: train num_bytes: 202129101 num_examples: 200 download_size: 202129101 dataset_size: 202129101 - config_name: sentiment_alignment features: - name: task dtype: string - name: ind dtype: int64 - name: positive_sample_tokenwise_loss list: float32 - name: negative_sample_tokenwise_loss list: float32 - name: prompt_sample_tokenwise_loss list: float32 - name: model_generated_continuation dtype: audio: sampling_rate: 16000 - name: positive_audio dtype: audio: sampling_rate: 16000 - name: negative_audio dtype: audio: sampling_rate: 16000 - name: positive_sample_raw_units dtype: - name: hubert dtype: string - name: negative_sample_raw_units dtype: - name: hubert dtype: string - name: prompt_audio dtype: audio: sampling_rate: 16000 - name: code_frame_rate dtype: int64 - name: code_depth dtype: int64 - name: model_sampling_rate dtype: int64 - name: ppl_sanity dtype: int64 - name: positive_continuation_tokenwise_loss dtype: 'null' - name: negative_continuation_tokenwise_loss dtype: 'null' - name: positive_continuation_raw_units dtype: - name: hubert dtype: string - name: negative_continuation_raw_units dtype: - name: hubert dtype: string - name: continuation_audio_positive dtype: audio: sampling_rate: 16000 - name: continuation_audio_negative dtype: audio: sampling_rate: 16000 splits: - name: train num_bytes: 46742156 num_examples: 200 download_size: 46742156 dataset_size: 46742156 - config_name: sentiment_consistency features: - name: task dtype: string - name: ind dtype: int64 - name: positive_sample_tokenwise_loss list: float32 - name: negative_sample_tokenwise_loss list: float32 - name: prompt_sample_tokenwise_loss list: float32 - name: model_generated_continuation dtype: audio: sampling_rate: 16000 - name: positive_audio dtype: audio: sampling_rate: 16000 - name: negative_audio dtype: audio: sampling_rate: 16000 - name: positive_sample_raw_units dtype: - name: hubert dtype: string - name: negative_sample_raw_units dtype: - name: hubert dtype: string - name: prompt_audio dtype: audio: sampling_rate: 16000 - name: code_frame_rate dtype: int64 - name: code_depth dtype: int64 - name: model_sampling_rate dtype: int64 - name: ppl_sanity dtype: int64 - name: positive_continuation_tokenwise_loss list: float64 - name: negative_continuation_tokenwise_loss list: float64 - name: positive_continuation_raw_units dtype: - name: hubert dtype: string - name: negative_continuation_raw_units dtype: - name: hubert dtype: string - name: continuation_audio_positive dtype: audio: sampling_rate: 16000 - name: continuation_audio_negative dtype: audio: sampling_rate: 16000 splits: - name: train num_bytes: 210124373 num_examples: 200 download_size: 210124373 dataset_size: 210124373 - config_name: speaker_consistency features: - name: task dtype: string - name: ind dtype: int64 - name: positive_sample_tokenwise_loss list: float32 - name: negative_sample_tokenwise_loss list: float32 - name: prompt_sample_tokenwise_loss list: float32 - name: model_generated_continuation dtype: audio: sampling_rate: 16000 - name: positive_audio dtype: audio: sampling_rate: 16000 - name: negative_audio dtype: audio: sampling_rate: 16000 - name: positive_sample_raw_units dtype: - name: hubert dtype: string - name: negative_sample_raw_units dtype: - name: hubert dtype: string - name: prompt_audio dtype: audio: sampling_rate: 16000 - name: code_frame_rate dtype: int64 - name: code_depth dtype: int64 - name: model_sampling_rate dtype: int64 - name: ppl_sanity dtype: int64 - name: positive_continuation_tokenwise_loss list: float64 - name: negative_continuation_tokenwise_loss list: float64 - name: positive_continuation_raw_units dtype: - name: hubert dtype: string - name: negative_continuation_raw_units dtype: - name: hubert dtype: string - name: continuation_audio_positive dtype: audio: sampling_rate: 16000 - name: continuation_audio_negative dtype: audio: sampling_rate: 16000 splits: - name: train num_bytes: 209864717 num_examples: 200 download_size: 209864717 dataset_size: 209864717 --- # SALMon Normalized Dataset This repo preserves the SALMon per-config folder layout while normalizing mismatched schema details across model families.

应用场景：