| | |
|---|
| | | # This is an example that demonstrates how to configure a model file. |
|---|
| | | # You can modify the configuration according to your own requirements. |
|---|
| | | |
|---|
| | | # to print the register_table: |
|---|
| | | # from funasr.register import tables |
|---|
| | | # tables.print() |
|---|
| | | |
|---|
| | | # network architecture |
|---|
| | | model: SenseVoice |
|---|
| | | model: SenseVoiceRWKV |
|---|
| | | model_conf: |
|---|
| | | lsm_weight: 0.1 |
|---|
| | | length_normalized_loss: true |
|---|
| | | hub: funasr |
|---|
| | | activation_checkpoint: true |
|---|
| | | sos: "<|startoftranscript|>" |
|---|
| | | eos: "<|endoftext|>" |
|---|
| | | downsample_rate: 4 |
|---|
| | | use_padmask: true |
|---|
| | | |
|---|
| | | dims: |
|---|
| | | n_mels: 128 |
|---|
| | | n_vocab: 60515 |
|---|
| | | n_audio_ctx: 1500 |
|---|
| | | n_audio_state: 1280 |
|---|
| | | n_audio_head: 20 |
|---|
| | | n_audio_layer: 32 |
|---|
| | | n_text_ctx: 448 |
|---|
| | | n_text_state: 1280 |
|---|
| | | n_text_head: 20 |
|---|
| | | n_text_layer: 32 |
|---|
| | | |
|---|
| | | |
|---|
| | | # decoder |
|---|
| | | decoder: SenseVoiceDecoder |
|---|
| | | decoder_conf: |
|---|
| | | rwkv_cfg: |
|---|
| | | n_embd: 1280 |
|---|
| | | dropout: 0 |
|---|
| | | head_size_a: 64 |
|---|
| | | ctx_len: 1280 |
|---|
| | | dim_att: 1280 #${model_conf.rwkv_cfg.n_embd} |
|---|
| | | dim_ffn: null |
|---|
| | | head_size_divisor: 8 |
|---|
| | | n_layer: 32 |
|---|
| | | pre_ffn: 0 |
|---|
| | | ln0: false |
|---|
| | | ln1: false |
|---|
| | | init_rwkv: false |
|---|
| | | datatype: bf16 |
|---|
| | | |
|---|
| | | # only use for hub == funasr, |
|---|
| | | # if hub == openai, dims is automaticall download |
|---|
| | | dims: |
|---|
| | | n_mels: 128 |
|---|
| | | n_vocab: 51866 |
|---|
| | | n_audio_ctx: 1500 |
|---|
| | | n_audio_state: 1280 |
|---|
| | | n_audio_head: 20 |
|---|
| | | n_audio_layer: 32 |
|---|
| | | n_text_ctx: 448 |
|---|
| | | n_text_state: 1280 |
|---|
| | | n_text_head: 20 |
|---|
| | | n_text_layer: 32 |
|---|
| | | |
|---|
| | | # frontend related |
|---|
| | | frontend: WhisperFrontend |
|---|
| | | frontend_conf: |
|---|
| | | fs: 16000 |
|---|
| | | n_mels: ${dims.n_mels} |
|---|
| | | do_pad_trim: true |
|---|
| | | n_mels: ${model_conf.dims.n_mels} |
|---|
| | | do_pad_trim: false |
|---|
| | | |
|---|
| | | tokenizer: WhisperTokenizer |
|---|
| | | tokenizer: SenseVoiceTokenizer |
|---|
| | | tokenizer_conf: |
|---|
| | | language: null |
|---|
| | | task: transcribe |
|---|
| | | vocab_path: null |
|---|
| | | is_multilingual: true |
|---|
| | | num_languages: 100 |
|---|
| | | num_languages: 8749 |
|---|
| | | |
|---|
| | | scope_map: [none, "model."] |
|---|
| | | dataset: SenseVoiceDataset |
|---|
| | | dataset_conf: |
|---|
| | | index_ds: IndexDSJsonlRankSplit |
|---|
| | | batch_sampler: EspnetStyleBatchSampler |
|---|
| | | rank_split: true |
|---|
| | | batch_type: token # example or length |
|---|
| | | batch_size: 3500 # if batch_type is example, batch_size is the numbers of samples; if length, batch_size is source_token_len+target_token_len; |
|---|
| | | max_token_length: 2200 |
|---|
| | | min_token_length: 60 |
|---|
| | | max_source_length: 2000 |
|---|
| | | min_source_length: 60 |
|---|
| | | max_target_length: 150 |
|---|
| | | min_target_length: 0 |
|---|
| | | shuffle: True |
|---|
| | | num_workers: 4 |
|---|
| | | sos: ${model_conf.sos} |
|---|
| | | eos: ${model_conf.eos} |
|---|
| | | |
|---|
| | | train_conf: |
|---|
| | | accum_grad: 2 |
|---|
| | | grad_clip: 5 |
|---|
| | | max_epoch: 20 |
|---|
| | | keep_nbest_models: 20 |
|---|
| | | avg_nbest_model: ${train_conf.keep_nbest_models} |
|---|
| | | log_interval: 50 |
|---|
| | | reset_gpu_cache: true |
|---|
| | | |
|---|
| | | optim: adamw |
|---|
| | | optim_conf: |
|---|
| | | lr: 0.00002 |
|---|
| | | |
|---|
| | | scheduler: warmuplr |
|---|
| | | scheduler_conf: |
|---|
| | | warmup_steps: 10000 |
|---|
| | | |
|---|
| | | specaug: SpecAug |
|---|
| | | specaug_conf: |
|---|
| | | apply_time_warp: true |
|---|
| | | time_warp_window: 5 |
|---|
| | | time_warp_mode: bicubic |
|---|
| | | apply_freq_mask: true |
|---|
| | | freq_mask_width_range: |
|---|
| | | - 0 |
|---|
| | | - 40 |
|---|
| | | num_freq_mask: 2 |
|---|
| | | apply_time_mask: true |
|---|
| | | time_mask_width_ratio_range: |
|---|
| | | - 0.0 |
|---|
| | | - 0.12 |
|---|
| | | num_time_mask: 2 |
|---|
| | | |
|---|
| | | scope_map: ['encoder.encoders', 'model.encoder', 'decoder.decoders', 'model.decoder'] |
|---|
