Upload 3 files

sensevoice_small_yue/config.yaml

@@ -0,0 +1,100 @@
+encoder: SenseVoiceEncoderSmall
+encoder_conf:
+  output_size: 512
+  attention_heads: 4
+  linear_units: 2048
+  num_blocks: 50
+  tp_blocks: 20
+  dropout_rate: 0.1
+  positional_dropout_rate: 0.1
+  attention_dropout_rate: 0.1
+  input_layer: pe
+  pos_enc_class: SinusoidalPositionEncoder
+  normalize_before: true
+  kernel_size: 11
+  sanm_shfit: 0
+  selfattention_layer_type: sanm
+model: SenseVoiceSmall
+model_conf:
+  length_normalized_loss: true
+  sos: 1
+  eos: 2
+  ignore_id: -1
+tokenizer: SentencepiecesTokenizer
+tokenizer_conf:
+  bpemodel: /home/work_nfs17/asr_data/ckpt/SenseVoiceSmall/chn_jpn_yue_eng_ko_spectok.bpe.model
+  unk_symbol: <unk>
+  split_with_space: true
+frontend: WavFrontend
+frontend_conf:
+  fs: 16000
+  window: hamming
+  n_mels: 80
+  frame_length: 25
+  frame_shift: 10
+  lfr_m: 7
+  lfr_n: 6
+  cmvn_file: /home/work_nfs17/asr_data/ckpt/SenseVoiceSmall/am.mvn
+dataset: SenseVoiceCTCDataset
+dataset_conf:
+  index_ds: IndexDSJsonl
+  batch_sampler: BatchSampler
+  data_split_num: 1
+  batch_type: token
+  batch_size: 18000
+  max_token_length: 2000
+  min_token_length: 60
+  max_source_length: 2000
+  min_source_length: 60
+  max_target_length: 200
+  min_target_length: 0
+  shuffle: true
+  num_workers: 4
+  sos: 1
+  eos: 2
+  IndexDSJsonl: IndexDSJsonl
+  retry: 20
+  sort_size: 1024
+train_conf:
+  accum_grad: 1
+  grad_clip: 5
+  max_epoch: 10
+  keep_nbest_models: 200
+  avg_nbest_model: 10
+  log_interval: 300
+  resume: true
+  validate_interval: 5000
+  save_checkpoint_interval: 5000
+  use_deepspeed: false
+  deepspeed_config: /home/work_nfs17/sywang/code/SenseVoice/deepspeed_conf/ds_stage1.json
+optim: adamw
+optim_conf:
+  lr: 0.0001
+scheduler: warmuplr
+scheduler_conf:
+  warmup_steps: 25000
+specaug: SpecAugLFR
+specaug_conf:
+  apply_time_warp: false
+  time_warp_window: 5
+  time_warp_mode: bicubic
+  apply_freq_mask: true
+  freq_mask_width_range:
+  - 0
+  - 30
+  lfr_rate: 6
+  num_freq_mask: 1
+  apply_time_mask: true
+  time_mask_width_range:
+  - 0
+  - 12
+  num_time_mask: 1
+init_param: /home/work_nfs17/asr_data/ckpt/SenseVoiceSmall/model.pt
+config: /home/work_nfs17/asr_data/ckpt/SenseVoiceSmall/config.yaml
+is_training: true
+trust_remote_code: false
+train_data_set_list: /home/work_nfs17/sywang/code/SenseVoice/data/open/stage2.jsonl
+valid_data_set_list: /home/work_nfs17/sywang/code/SenseVoice/data/val.jsonl
+output_dir: ./outputs5
+model_path: /home/work_nfs17/asr_data/ckpt/SenseVoiceSmall
+device: cpu

sensevoice_small_yue/configuration.json

@@ -0,0 +1,14 @@
+{
+  "framework": "pytorch",
+  "task" : "auto-speech-recognition",
+  "model": {"type" : "funasr"},
+  "pipeline": {"type":"funasr-pipeline"},
+  "model_name_in_hub": {
+    "ms":"", 
+    "hf":""},
+  "file_path_metas": {
+    "init_param":"model.pt", 
+    "config":"config.yaml",
+    "tokenizer_conf": {"bpemodel": "chn_jpn_yue_eng_ko_spectok.bpe.model"},
+    "frontend_conf":{"cmvn_file": "am.mvn"}}
+}

sensevoice_small_yue/model.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:38940ad5ae8a580efef0069f6a9c38ac67656dd8f046af9bd8d162cea3448706
+size 2809073798