| model: | |
| _target_: modules.sensevoice.model.SenseVoice | |
| model: | |
| _target_: modules.sensevoice.sensevoicesmall.SenseVoiceSmall | |
| specaug: | |
| _target_: modules.sensevoice.specaug.SpecAugLFR | |
| apply_freq_mask: true | |
| apply_time_mask: true | |
| apply_time_warp: false | |
| freq_mask_width_range: [0, 30] | |
| lfr_rate: 6 | |
| num_freq_mask: 1 | |
| num_time_mask: 1 | |
| time_mask_width_range: [0, 12] | |
| time_warp_mode: bicubic | |
| time_warp_window: 5 | |
| encoder: | |
| _target_: modules.sensevoice.sensevoicesmall.SenseVoiceEncoderSmall | |
| attention_dropout_rate: 0.1 | |
| attention_heads: 4 | |
| dropout_rate: 0.1 | |
| kernel_size: 11 | |
| linear_units: 2048 | |
| normalize_before: true | |
| num_blocks: 50 | |
| output_size: 512 | |
| sanm_shfit: 0 | |
| tp_blocks: 20 | |
| input_size: 560 | |
| tokenizer: | |
| _target_: modules.sensevoice.tokenizer.SentencepiecesTokenizer | |
| bpemodel: /storage-root/datasets/zhaojingtong/checkpoints/sensevoice/chn_jpn_yue_eng_ko_spectok.bpe.model | |
| unk_symbol: <unk> | |
| split_with_space: true | |
| frontend: | |
| _target_: modules.sensevoice.frontend.WavFrontend | |
| fs: 16000 | |
| window: hamming | |
| n_mels: 80 | |
| frame_length: 25 | |
| frame_shift: 10 | |
| lfr_m: 7 | |
| lfr_n: 6 | |
| length_normalized_loss: true | |
| input_size: 560 | |
| vocab_size: 25055 | |
| sos: 1 | |
| eos: 2 | |
| ignore_id: -1 | |
| vad_model: | |
| _target_: modules.sensevoice.vad.FsmnVADStreaming | |
| encoder: | |
| _target_: modules.sensevoice.vad.FSMN | |
| input_dim: 400 | |
| input_affine_dim: 140 | |
| fsmn_layers: 4 | |
| linear_dim: 250 | |
| proj_dim: 128 | |
| lorder: 20 | |
| rorder: 0 | |
| lstride: 1 | |
| rstride: 0 | |
| output_affine_dim: 140 | |
| output_dim: 248 | |
| frontend: | |
| _target_: modules.sensevoice.frontend.WavFrontendOnline | |
| fs: 16000 | |
| window: hamming | |
| n_mels: 80 | |
| frame_length: 25 | |
| frame_shift: 10 | |
| dither: 0.0 | |
| lfr_m: 5 | |
| lfr_n: 1 | |
| cmvn_file: /storage-root/datasets/zhaojingtong/checkpoints/sensevoice/am.mvn | |
| sample_rate: 16000 | |
| detect_mode: 1 | |
| snr_mode: 0 | |
| max_end_silence_time: 800 | |
| max_start_silence_time: 3000 | |
| do_start_point_detection: True | |
| do_end_point_detection: True | |
| window_size_ms: 200 | |
| sil_to_speech_time_thres: 150 | |
| speech_to_sil_time_thres: 150 | |
| speech_2_noise_ratio: 1.0 | |
| do_extend: 1 | |
| lookback_time_start_point: 200 | |
| lookahead_time_end_point: 100 | |
| max_single_segment_time: 60000 | |
| snr_thres: -100.0 | |
| noise_frame_num_used_for_snr: 100 | |
| decibel_thres: -100.0 | |
| speech_noise_thres: 0.6 | |
| fe_prior_thres: 0.0001 | |
| silence_pdf_num: 1 | |
| sil_pdf_ids: [0] | |
| speech_noise_thresh_low: -0.1 | |
| speech_noise_thresh_high: 0.3 | |
| output_frame_probs: False | |
| frame_in_ms: 10 | |
| frame_length_ms: 25 | |
| tokenizer: None | |
| vocab_size: -1 | |
| input_size: 400 | |
| kwargs: | |
| specaug: | |
| apply_freq_mask: true | |
| apply_time_mask: true | |
| apply_time_warp: false | |
| freq_mask_width_range: [0, 30] | |
| lfr_rate: 6 | |
| num_freq_mask: 1 | |
| num_time_mask: 1 | |
| time_mask_width_range: [0, 12] | |
| time_warp_mode: bicubic | |
| time_warp_window: 5 | |
| encoder: | |
| attention_dropout_rate: 0.1 | |
| attention_heads: 4 | |
| dropout_rate: 0.1 | |
| kernel_size: 11 | |
| linear_units: 2048 | |
| normalize_before: true | |
| num_blocks: 50 | |
| output_size: 512 | |
| sanm_shfit: 0 | |
| tp_blocks: 20 | |
| input_size: 560 | |
| tokenizer: | |
| bpemodel: /storage-root/datasets/zhaojingtong/checkpoints/sensevoice/chn_jpn_yue_eng_ko_spectok.bpe.model | |
| unk_symbol: <unk> | |
| split_with_space: true | |
| frontend: | |
| fs: 16000 | |
| window: hamming | |
| n_mels: 80 | |
| frame_length: 25 | |
| frame_shift: 10 | |
| lfr_m: 7 | |
| lfr_n: 6 | |
| length_normalized_loss: true | |
| input_size: 560 | |
| vocab_size: 25055 | |
| sos: 1 | |
| eos: 2 | |
| ignore_id: -1 | |
| vad_kwargs: | |
| encoder: | |
| input_dim: 400 | |
| input_affine_dim: 140 | |
| fsmn_layers: 4 | |
| linear_dim: 250 | |
| proj_dim: 128 | |
| lorder: 20 | |
| rorder: 0 | |
| lstride: 1 | |
| rstride: 0 | |
| output_affine_dim: 140 | |
| output_dim: 248 | |
| frontend: | |
| fs: 16000 | |
| window: hamming | |
| n_mels: 80 | |
| frame_length: 25 | |
| frame_shift: 10 | |
| dither: 0.0 | |
| lfr_m: 5 | |
| lfr_n: 1 | |
| cmvn_file: /storage-root/datasets/zhaojingtong/checkpoints/sensevoice/am.mvn | |
| sample_rate: 16000 | |
| detect_mode: 1 | |
| snr_mode: 0 | |
| max_end_silence_time: 800 | |
| max_start_silence_time: 3000 | |
| do_start_point_detection: True | |
| do_end_point_detection: True | |
| window_size_ms: 200 | |
| sil_to_speech_time_thres: 150 | |
| speech_to_sil_time_thres: 150 | |
| speech_2_noise_ratio: 1.0 | |
| do_extend: 1 | |
| lookback_time_start_point: 200 | |
| lookahead_time_end_point: 100 | |
| max_single_segment_time: 60000 | |
| snr_thres: -100.0 | |
| noise_frame_num_used_for_snr: 100 | |
| decibel_thres: -100.0 | |
| speech_noise_thres: 0.6 | |
| fe_prior_thres: 0.0001 | |
| silence_pdf_num: 1 | |
| sil_pdf_ids: [0] | |
| speech_noise_thresh_low: -0.1 | |
| speech_noise_thresh_high: 0.3 | |
| output_frame_probs: False | |
| frame_in_ms: 10 | |
| frame_length_ms: 25 | |
| tokenizer: None | |
| vocab_size: -1 | |
| input_size: 400 |