Add files using upload-large-folder tool

.gitattributes

@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+2024-10-25/18-23-57/train_ds.log filter=lfs diff=lfs merge=lfs -text
+model.pt.best filter=lfs diff=lfs merge=lfs -text

.ipynb_checkpoints/config-checkpoint.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: /root/.cache/modelscope/hub/iic/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: /root/.cache/modelscope/hub/iic/SenseVoiceSmall/am.mvn
+dataset: SenseVoiceCTCDataset
+dataset_conf:
+  index_ds: IndexDSJsonl
+  batch_sampler: BatchSampler
+  data_split_num: 1
+  batch_type: token
+  batch_size: 25000
+  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: 100
+  keep_nbest_models: 10
+  avg_nbest_model: 10
+  log_interval: 1
+  resume: true
+  validate_interval: 2000
+  save_checkpoint_interval: 2000
+  use_deepspeed: false
+  deepspeed_config: /root/autodl-tmp/SenseVoice/deepspeed_conf/ds_stage1.json
+optim: adamw
+optim_conf:
+  lr: 0.0002
+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: /root/.cache/modelscope/hub/iic/SenseVoiceSmall/model.pt
+config: /root/.cache/modelscope/hub/iic/SenseVoiceSmall/config.yaml
+is_training: true
+trust_remote_code: true
+train_data_set_list: /root/autodl-tmp/train/train.jsonl
+valid_data_set_list: /root/autodl-tmp/val/val.jsonl
+output_dir: ./outputs
+model_path: /root/.cache/modelscope/hub/iic/SenseVoiceSmall
+device: cpu

2024-10-25/18-23-57/.hydra/config.yaml

@@ -0,0 +1,24 @@
+model: iic/SenseVoiceSmall
+trust_remote_code: true
+train_data_set_list: /root/autodl-tmp/train/train.jsonl
+valid_data_set_list: /root/autodl-tmp/val/val.jsonl
+dataset_conf:
+  data_split_num: 1
+  batch_sampler: BatchSampler
+  batch_size: 25000
+  sort_size: 1024
+  batch_type: token
+  num_workers: 4
+train_conf:
+  max_epoch: 100
+  log_interval: 1
+  resume: true
+  validate_interval: 2000
+  save_checkpoint_interval: 2000
+  keep_nbest_models: 10
+  avg_nbest_model: 10
+  use_deepspeed: false
+  deepspeed_config: /root/autodl-tmp/SenseVoice/deepspeed_conf/ds_stage1.json
+optim_conf:
+  lr: 0.0002
+output_dir: ./outputs

2024-10-25/18-23-57/.hydra/hydra.yaml

@@ -0,0 +1,172 @@
+hydra:
+  run:
+    dir: outputs/${now:%Y-%m-%d}/${now:%H-%M-%S}
+  sweep:
+    dir: multirun/${now:%Y-%m-%d}/${now:%H-%M-%S}
+    subdir: ${hydra.job.num}
+  launcher:
+    _target_: hydra._internal.core_plugins.basic_launcher.BasicLauncher
+  sweeper:
+    _target_: hydra._internal.core_plugins.basic_sweeper.BasicSweeper
+    max_batch_size: null
+    params: null
+  help:
+    app_name: ${hydra.job.name}
+    header: '${hydra.help.app_name} is powered by Hydra.
+
+      '
+    footer: 'Powered by Hydra (https://hydra.cc)
+
+      Use --hydra-help to view Hydra specific help
+
+      '
+    template: '${hydra.help.header}
+
+      == Configuration groups ==
+
+      Compose your configuration from those groups (group=option)
+
+
+      $APP_CONFIG_GROUPS
+
+
+      == Config ==
+
+      Override anything in the config (foo.bar=value)
+
+
+      $CONFIG
+
+
+      ${hydra.help.footer}
+
+      '
+  hydra_help:
+    template: 'Hydra (${hydra.runtime.version})
+
+      See https://hydra.cc for more info.
+
+
+      == Flags ==
+
+      $FLAGS_HELP
+
+
+      == Configuration groups ==
+
+      Compose your configuration from those groups (For example, append hydra/job_logging=disabled
+      to command line)
+
+
+      $HYDRA_CONFIG_GROUPS
+
+
+      Use ''--cfg hydra'' to Show the Hydra config.
+
+      '
+    hydra_help: ???
+  hydra_logging:
+    version: 1
+    formatters:
+      simple:
+        format: '[%(asctime)s][HYDRA] %(message)s'
+    handlers:
+      console:
+        class: logging.StreamHandler
+        formatter: simple
+        stream: ext://sys.stdout
+    root:
+      level: INFO
+      handlers:
+      - console
+    loggers:
+      logging_example:
+        level: DEBUG
+    disable_existing_loggers: false
+  job_logging:
+    version: 1
+    formatters:
+      simple:
+        format: '[%(asctime)s][%(name)s][%(levelname)s] - %(message)s'
+    handlers:
+      console:
+        class: logging.StreamHandler
+        formatter: simple
+        stream: ext://sys.stdout
+      file:
+        class: logging.FileHandler
+        formatter: simple
+        filename: ${hydra.runtime.output_dir}/${hydra.job.name}.log
+    root:
+      level: INFO
+      handlers:
+      - console
+      - file
+    disable_existing_loggers: false
+  env: {}
+  mode: RUN
+  searchpath: []
+  callbacks: {}
+  output_subdir: .hydra
+  overrides:
+    hydra:
+    - hydra.mode=RUN
+    task:
+    - ++model=iic/SenseVoiceSmall
+    - ++trust_remote_code=true
+    - ++train_data_set_list=/root/autodl-tmp/train/train.jsonl
+    - ++valid_data_set_list=/root/autodl-tmp/val/val.jsonl
+    - ++dataset_conf.data_split_num=1
+    - ++dataset_conf.batch_sampler=BatchSampler
+    - ++dataset_conf.batch_size=25000
+    - ++dataset_conf.sort_size=1024
+    - ++dataset_conf.batch_type=token
+    - ++dataset_conf.num_workers=4
+    - ++train_conf.max_epoch=100
+    - ++train_conf.log_interval=1
+    - ++train_conf.resume=true
+    - ++train_conf.validate_interval=2000
+    - ++train_conf.save_checkpoint_interval=2000
+    - ++train_conf.keep_nbest_models=10
+    - ++train_conf.avg_nbest_model=10
+    - ++train_conf.use_deepspeed=false
+    - ++train_conf.deepspeed_config=/root/autodl-tmp/SenseVoice/deepspeed_conf/ds_stage1.json
+    - ++optim_conf.lr=0.0002
+    - ++output_dir=./outputs
+  job:
+    name: train_ds
+    chdir: null
+    override_dirname: ++dataset_conf.batch_sampler=BatchSampler,++dataset_conf.batch_size=25000,++dataset_conf.batch_type=token,++dataset_conf.data_split_num=1,++dataset_conf.num_workers=4,++dataset_conf.sort_size=1024,++model=iic/SenseVoiceSmall,++optim_conf.lr=0.0002,++output_dir=./outputs,++train_conf.avg_nbest_model=10,++train_conf.deepspeed_config=/root/autodl-tmp/SenseVoice/deepspeed_conf/ds_stage1.json,++train_conf.keep_nbest_models=10,++train_conf.log_interval=1,++train_conf.max_epoch=100,++train_conf.resume=true,++train_conf.save_checkpoint_interval=2000,++train_conf.use_deepspeed=false,++train_conf.validate_interval=2000,++train_data_set_list=/root/autodl-tmp/train/train.jsonl,++trust_remote_code=true,++valid_data_set_list=/root/autodl-tmp/val/val.jsonl
+    id: ???
+    num: ???
+    config_name: null
+    env_set: {}
+    env_copy: []
+    config:
+      override_dirname:
+        kv_sep: '='
+        item_sep: ','
+        exclude_keys: []
+  runtime:
+    version: 1.3.2
+    version_base: '1.3'
+    cwd: /root/autodl-tmp/SenseVoice
+    config_sources:
+    - path: hydra.conf
+      schema: pkg
+      provider: hydra
+    - path: ''
+      schema: structured
+      provider: schema
+    output_dir: /root/autodl-tmp/SenseVoice/outputs/2024-10-25/18-23-57
+    choices:
+      hydra/env: default
+      hydra/callbacks: null
+      hydra/job_logging: default
+      hydra/hydra_logging: default
+      hydra/hydra_help: default
+      hydra/help: default
+      hydra/sweeper: basic
+      hydra/launcher: basic
+      hydra/output: default
+  verbose: false

2024-10-25/18-23-57/.hydra/overrides.yaml

@@ -0,0 +1,21 @@
+- ++model=iic/SenseVoiceSmall
+- ++trust_remote_code=true
+- ++train_data_set_list=/root/autodl-tmp/train/train.jsonl
+- ++valid_data_set_list=/root/autodl-tmp/val/val.jsonl
+- ++dataset_conf.data_split_num=1
+- ++dataset_conf.batch_sampler=BatchSampler
+- ++dataset_conf.batch_size=25000
+- ++dataset_conf.sort_size=1024
+- ++dataset_conf.batch_type=token
+- ++dataset_conf.num_workers=4
+- ++train_conf.max_epoch=100
+- ++train_conf.log_interval=1
+- ++train_conf.resume=true
+- ++train_conf.validate_interval=2000
+- ++train_conf.save_checkpoint_interval=2000
+- ++train_conf.keep_nbest_models=10
+- ++train_conf.avg_nbest_model=10
+- ++train_conf.use_deepspeed=false
+- ++train_conf.deepspeed_config=/root/autodl-tmp/SenseVoice/deepspeed_conf/ds_stage1.json
+- ++optim_conf.lr=0.0002
+- ++output_dir=./outputs

2024-10-25/18-23-57/train_ds.log

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:078bf9a7f021d04db46a4ab17a2f56246473f90ea4a12da0afd619f81f0dd4f0
+size 30254298

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: /root/.cache/modelscope/hub/iic/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: /root/.cache/modelscope/hub/iic/SenseVoiceSmall/am.mvn
+dataset: SenseVoiceCTCDataset
+dataset_conf:
+  index_ds: IndexDSJsonl
+  batch_sampler: BatchSampler
+  data_split_num: 1
+  batch_type: token
+  batch_size: 25000
+  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: 100
+  keep_nbest_models: 10
+  avg_nbest_model: 10
+  log_interval: 1
+  resume: true
+  validate_interval: 2000
+  save_checkpoint_interval: 2000
+  use_deepspeed: false
+  deepspeed_config: /root/autodl-tmp/SenseVoice/deepspeed_conf/ds_stage1.json
+optim: adamw
+optim_conf:
+  lr: 0.0002
+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: /root/.cache/modelscope/hub/iic/SenseVoiceSmall/model.pt
+config: /root/.cache/modelscope/hub/iic/SenseVoiceSmall/config.yaml
+is_training: true
+trust_remote_code: true
+train_data_set_list: /root/autodl-tmp/train/train.jsonl
+valid_data_set_list: /root/autodl-tmp/val/val.jsonl
+output_dir: ./outputs
+model_path: /root/.cache/modelscope/hub/iic/SenseVoiceSmall
+device: cpu

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"}}
+}

model.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:10fbed6aefd3504b48631b3060874b09a57f821c01111ab008a6fc32a1565368
+size 2809076230

model.pt.best

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:39da396056cc8340fe784419407a7266ae2d3529196b958d38460f80ce02cdf0
+size 2809131854

tensorboard/events.out.tfevents.1729851842.autodl-container-f42f45a886-bccfcaff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61cd5645cb0a0457120b60d539673b4782db7d60b033f87cfa59bee0d82aafa3
+size 37220360