Name: SpeechPPL/SALMon_TWIST-350M-normalized
Creator: SpeechPPL
Published: 2026-04-16 12:58:51
License: 暂无描述

下载链接：

https://hf-mirror.com/datasets/SpeechPPL/SALMon_TWIST-350M-normalized

下载链接

链接失效反馈

官方服务：

资源简介：

--- configs: - config_name: bg_alignment data_files: - split: train path: bg_alignment/train-* - config_name: bg_all_consistency data_files: - split: train path: bg_all_consistency/train-* - config_name: bg_domain_consistency data_files: - split: train path: bg_domain_consistency/train-* - config_name: gender_consistency data_files: - split: train path: gender_consistency/train-* - config_name: rir_consistency data_files: - split: train path: rir_consistency/train-* - config_name: sentiment_alignment data_files: - split: train path: sentiment_alignment/train-* - config_name: sentiment_consistency data_files: - split: train path: sentiment_consistency/train-* - config_name: speaker_consistency data_files: - split: train path: speaker_consistency/train-* dataset_info: - config_name: bg_alignment features: - name: task dtype: string - name: ind dtype: int64 - name: positive_audio dtype: audio - name: negative_audio dtype: audio - name: prompt_audio dtype: audio: sampling_rate: 16000 - name: continuation_audio_positive dtype: audio: sampling_rate: 16000 - name: continuation_audio_negative dtype: audio: sampling_rate: 16000 - name: negative_audio_sanity dtype: audio: sampling_rate: 16000 - name: positive_sample_tokenwise_loss sequence: float32 - name: positive_sample_raw_units sequence: int32 - name: negative_sample_tokenwise_loss sequence: float32 - name: negative_sample_raw_units sequence: int32 - name: code_frame_rate dtype: int64 - name: code_depth dtype: int64 - name: offset sequence: int64 - name: model_sampling_rate sequence: int64 - name: ppl_sanity dtype: int64 - name: model_generated_continuation dtype: audio: sampling_rate: 16000 splits: - name: train num_bytes: 86758152 num_examples: 200 download_size: 86758152 dataset_size: 86758152 - config_name: bg_all_consistency features: - name: task dtype: string - name: ind dtype: int64 - name: positive_audio dtype: audio - name: negative_audio dtype: audio - name: audio_transition_s dtype: int64 - name: prompt_audio dtype: audio: sampling_rate: 16000 - name: continuation_audio_positive dtype: audio: sampling_rate: 16000 - name: continuation_audio_negative dtype: audio: sampling_rate: 16000 - name: negative_audio_sanity dtype: audio: sampling_rate: 16000 - name: positive_sample_tokenwise_loss sequence: float32 - name: positive_sample_raw_units sequence: int32 - name: negative_sample_tokenwise_loss sequence: float32 - name: negative_sample_raw_units sequence: int32 - name: prompt_sample_tokenwise_loss sequence: float32 - name: prompt_sample_raw_units sequence: int32 - name: positive_continuation_tokenwise_loss sequence: float32 - name: positive_continuation_raw_units sequence: int32 - name: negative_continuation_tokenwise_loss sequence: float32 - name: negative_continuation_raw_units sequence: int32 - name: model_generated_continuation dtype: audio: sampling_rate: 16000 - name: code_frame_rate dtype: int64 - name: code_depth dtype: int64 - name: offset sequence: int64 - name: model_sampling_rate sequence: int64 - name: ppl_sanity dtype: int64 splits: - name: train num_bytes: 233065267 num_examples: 200 download_size: 233065267 dataset_size: 233065267 - config_name: bg_domain_consistency features: - name: task dtype: string - name: ind dtype: int64 - name: positive_audio dtype: audio - name: negative_audio dtype: audio - name: audio_transition_s dtype: int64 - name: prompt_audio dtype: audio: sampling_rate: 16000 - name: continuation_audio_positive dtype: audio: sampling_rate: 16000 - name: continuation_audio_negative dtype: audio: sampling_rate: 16000 - name: negative_audio_sanity dtype: audio: sampling_rate: 16000 - name: positive_sample_tokenwise_loss sequence: float32 - name: positive_sample_raw_units sequence: int32 - name: negative_sample_tokenwise_loss sequence: float32 - name: negative_sample_raw_units sequence: int32 - name: prompt_sample_tokenwise_loss sequence: float32 - name: prompt_sample_raw_units sequence: int32 - name: positive_continuation_tokenwise_loss sequence: float32 - name: positive_continuation_raw_units sequence: int32 - name: negative_continuation_tokenwise_loss sequence: float32 - name: negative_continuation_raw_units sequence: int32 - name: model_generated_continuation dtype: audio: sampling_rate: 16000 - name: code_frame_rate dtype: int64 - name: code_depth dtype: int64 - name: offset sequence: int64 - name: model_sampling_rate sequence: int64 - name: ppl_sanity dtype: int64 splits: - name: train num_bytes: 235965681 num_examples: 200 download_size: 235965681 dataset_size: 235965681 - config_name: gender_consistency features: - name: task dtype: string - name: ind dtype: int64 - name: positive_audio dtype: audio - name: negative_audio dtype: audio - name: audio_transition_s dtype: int64 - name: prompt_audio dtype: audio: sampling_rate: 16000 - name: continuation_audio_positive dtype: audio: sampling_rate: 16000 - name: continuation_audio_negative dtype: audio: sampling_rate: 16000 - name: negative_audio_sanity dtype: audio: sampling_rate: 16000 - name: positive_sample_tokenwise_loss sequence: float32 - name: positive_sample_raw_units sequence: int32 - name: negative_sample_tokenwise_loss sequence: float32 - name: negative_sample_raw_units sequence: int32 - name: prompt_sample_tokenwise_loss sequence: float32 - name: prompt_sample_raw_units sequence: int32 - name: positive_continuation_tokenwise_loss sequence: float32 - name: positive_continuation_raw_units sequence: int32 - name: negative_continuation_tokenwise_loss sequence: float32 - name: negative_continuation_raw_units sequence: int32 - name: model_generated_continuation dtype: audio: sampling_rate: 16000 - name: code_frame_rate dtype: int64 - name: code_depth dtype: int64 - name: offset sequence: int64 - name: model_sampling_rate sequence: int64 - name: ppl_sanity dtype: int64 splits: - name: train num_bytes: 234716857 num_examples: 200 download_size: 234716857 dataset_size: 234716857 - config_name: rir_consistency features: - name: task dtype: string - name: ind dtype: int64 - name: positive_audio dtype: audio - name: negative_audio dtype: audio - name: audio_transition_s dtype: int64 - name: prompt_audio dtype: audio: sampling_rate: 16000 - name: continuation_audio_positive dtype: audio: sampling_rate: 16000 - name: continuation_audio_negative dtype: audio: sampling_rate: 16000 - name: negative_audio_sanity dtype: audio: sampling_rate: 16000 - name: positive_sample_tokenwise_loss sequence: float32 - name: positive_sample_raw_units sequence: int32 - name: negative_sample_tokenwise_loss sequence: float32 - name: negative_sample_raw_units sequence: int32 - name: prompt_sample_tokenwise_loss sequence: float32 - name: prompt_sample_raw_units sequence: int32 - name: positive_continuation_tokenwise_loss sequence: float32 - name: positive_continuation_raw_units sequence: int32 - name: negative_continuation_tokenwise_loss sequence: float32 - name: negative_continuation_raw_units sequence: int32 - name: model_generated_continuation dtype: audio: sampling_rate: 16000 - name: code_frame_rate dtype: int64 - name: code_depth dtype: int64 - name: offset sequence: int64 - name: model_sampling_rate sequence: int64 - name: ppl_sanity dtype: int64 splits: - name: train num_bytes: 217254768 num_examples: 200 download_size: 217254768 dataset_size: 217254768 - config_name: sentiment_alignment features: - name: task dtype: string - name: ind dtype: int64 - name: positive_audio dtype: audio - name: negative_audio dtype: audio - name: prompt_audio dtype: audio: sampling_rate: 16000 - name: continuation_audio_positive dtype: audio: sampling_rate: 16000 - name: continuation_audio_negative dtype: audio: sampling_rate: 16000 - name: negative_audio_sanity dtype: audio: sampling_rate: 16000 - name: positive_sample_tokenwise_loss sequence: float32 - name: positive_sample_raw_units sequence: int32 - name: negative_sample_tokenwise_loss sequence: float32 - name: negative_sample_raw_units sequence: int32 - name: code_frame_rate dtype: int64 - name: code_depth dtype: int64 - name: offset sequence: int64 - name: model_sampling_rate sequence: int64 - name: ppl_sanity dtype: int64 - name: model_generated_continuation dtype: audio: sampling_rate: 16000 splits: - name: train num_bytes: 46579503 num_examples: 200 download_size: 46579503 dataset_size: 46579503 - config_name: sentiment_consistency features: - name: task dtype: string - name: ind dtype: int64 - name: positive_audio dtype: audio - name: negative_audio dtype: audio - name: audio_transition_s dtype: int64 - name: prompt_audio dtype: audio: sampling_rate: 16000 - name: continuation_audio_positive dtype: audio: sampling_rate: 16000 - name: continuation_audio_negative dtype: audio: sampling_rate: 16000 - name: negative_audio_sanity dtype: audio: sampling_rate: 16000 - name: positive_sample_tokenwise_loss sequence: float32 - name: positive_sample_raw_units sequence: int32 - name: negative_sample_tokenwise_loss sequence: float32 - name: negative_sample_raw_units sequence: int32 - name: prompt_sample_tokenwise_loss sequence: float32 - name: prompt_sample_raw_units sequence: int32 - name: positive_continuation_tokenwise_loss sequence: float32 - name: positive_continuation_raw_units sequence: int32 - name: negative_continuation_tokenwise_loss sequence: float32 - name: negative_continuation_raw_units sequence: int32 - name: model_generated_continuation dtype: audio: sampling_rate: 16000 - name: code_frame_rate dtype: int64 - name: code_depth dtype: int64 - name: offset sequence: int64 - name: model_sampling_rate sequence: int64 - name: ppl_sanity dtype: int64 splits: - name: train num_bytes: 231182568 num_examples: 200 download_size: 231182568 dataset_size: 231182568 - config_name: speaker_consistency features: - name: task dtype: string - name: ind dtype: int64 - name: positive_audio dtype: audio - name: negative_audio dtype: audio - name: audio_transition_s dtype: int64 - name: prompt_audio dtype: audio: sampling_rate: 16000 - name: continuation_audio_positive dtype: audio: sampling_rate: 16000 - name: continuation_audio_negative dtype: audio: sampling_rate: 16000 - name: negative_audio_sanity dtype: audio: sampling_rate: 16000 - name: positive_sample_tokenwise_loss sequence: float32 - name: positive_sample_raw_units sequence: int32 - name: negative_sample_tokenwise_loss sequence: float32 - name: negative_sample_raw_units sequence: int32 - name: prompt_sample_tokenwise_loss sequence: float32 - name: prompt_sample_raw_units sequence: int32 - name: positive_continuation_tokenwise_loss sequence: float32 - name: positive_continuation_raw_units sequence: int32 - name: negative_continuation_tokenwise_loss sequence: float32 - name: negative_continuation_raw_units sequence: int32 - name: model_generated_continuation dtype: audio: sampling_rate: 16000 - name: code_frame_rate dtype: int64 - name: code_depth dtype: int64 - name: offset sequence: int64 - name: model_sampling_rate sequence: int64 - name: ppl_sanity dtype: int64 splits: - name: train num_bytes: 235005925 num_examples: 200 download_size: 235005925 dataset_size: 235005925 --- # SALMon Normalized Dataset This repo preserves the SALMon per-config folder layout while normalizing mismatched schema details across model families.

应用场景：