| | |
|---|
| | | init_param_path: "/nfs/maziyang.mzy/models/vicuna-7b-v1.5" |
|---|
| | | freeze: true |
|---|
| | | |
|---|
| | | adaptor: linear |
|---|
| | | adaptor: Linear |
|---|
| | | adaptor_conf: |
|---|
| | | downsample_rate: 1 |
|---|
| | | llm_dim: 4096 |
|---|
| | | encoder_dim: 2048 |
|---|
| | | encoder_dim: 512 |
|---|
| | | |
|---|
| | | # frontend related |
|---|
| | | frontend: WavFrontend |
|---|
| | |
|---|
| | | n_mels: 80 |
|---|
| | | frame_length: 25 |
|---|
| | | frame_shift: 10 |
|---|
| | | dither: 0.0 |
|---|
| | | lfr_m: 1 |
|---|
| | | lfr_n: 1 |
|---|
| | | lfr_m: 7 |
|---|
| | | lfr_n: 6 |
|---|
| | | cmvn_file: "/root/.cache/modelscope/hub/iic/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/am.mvn" |
|---|
| | | |
|---|
| | | specaug: SpecAug |
|---|
| | | specaug: SpecAugLFR |
|---|
| | | specaug_conf: |
|---|
| | | apply_time_warp: true |
|---|
| | | apply_time_warp: false |
|---|
| | | time_warp_window: 5 |
|---|
| | | time_warp_mode: bicubic |
|---|
| | | apply_freq_mask: true |
|---|
| | | freq_mask_width_range: |
|---|
| | | - 0 |
|---|
| | | - 30 |
|---|
| | | num_freq_mask: 2 |
|---|
| | | lfr_rate: 6 |
|---|
| | | num_freq_mask: 1 |
|---|
| | | apply_time_mask: true |
|---|
| | | time_mask_width_range: |
|---|
| | | - 0 |
|---|
| | | - 40 |
|---|
| | | num_time_mask: 2 |
|---|
| | | - 12 |
|---|
| | | num_time_mask: 1 |
|---|
| | | |
|---|
| | | train_conf: |
|---|
| | | accum_grad: 1 |
|---|
| | | grad_clip: 5 |
|---|
| | | max_epoch: 150 |
|---|
| | | keep_nbest_models: 10 |
|---|
| | | log_interval: 50 |
|---|
| | | log_interval: 10 |
|---|
| | | |
|---|
| | | optim: adam |
|---|
| | | optim: adamw |
|---|
| | | optim_conf: |
|---|
| | | lr: 0.001 |
|---|
| | | lr: 0.0001 |
|---|
| | | weight_decay: 0.000001 |
|---|
| | | scheduler: warmuplr |
|---|
| | | scheduler_conf: |
|---|
| | | warmup_steps: 35000 |
|---|
| | | warmup_steps: 1500 |
|---|
| | | |
|---|
| | | dataset: AudioLLMDataset |
|---|
| | | dataset_conf: |
|---|
| | | index_ds: IndexDSJsonl |
|---|
| | | batch_sampler: RankFullLocalShuffleBatchSampler |
|---|
| | | batch_type: example # example or length |
|---|
| | | batch_size: 4 # if batch_type is example, batch_size is the numbers of samples; if length, batch_size is source_token_len+target_token_len; |
|---|
| | | batch_size: 8 # 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: 2048 # filter samples if source_token_len+target_token_len > max_token_length, |
|---|
| | | buffer_size: 500 |
|---|
| | | shuffle: True |
|---|
| | | num_workers: 4 |
|---|
| | | preprocessor_text: TextPreprocessRemovePunctuation |
|---|
| | | |
|---|
| | | tokenizer: HuggingfaceTokenizer |
|---|
| | | tokenizer_conf: |
|---|
| | | unk_symbol: <unk> |
|---|
| | | init_param_path: null |
|---|
| | | init_param_path: "/nfs/maziyang.mzy/models/vicuna-7b-v1.5" |
|---|
| | | |
|---|
