model_config.yaml

name: whisper_speech_recognition
config_type: model
vocab_size: 51865
num_mel_bins: 80
encoder_layers: 12
encoder_attention_heads: 12
decoder_layers: 12
decoder_attention_heads: 12
num_hidden_layers: 12
decoder_ffn_dim: 3072
encoder_ffn_dim: 3072
encoder_layerdrop: 0.0
decoder_layerdrop: 0.0
decoder_start_token_id: 50258
use_cache: false
sampling_rate: 16000
is_encoder_decoder: true
activation_function: gelu
d_model: 768
dropout: 0.0
torch_dtype: float32
attention_dropout: 0.0
activation_dropout: 0.0
init_std: 0.02
scale_embedding: false
max_source_positions: 1500
max_target_positions: 448
pad_token_id: 50257
bos_token_id: 50257
eos_token_id: 50257
suppress_tokens: []
begin_suppress_tokens:
- 220
- 50257
use_weighted_layer_sum: false
classifier_proj_size: 256
apply_spec_augment: false
mask_time_prob: 0.05
mask_time_length: 10
mask_time_min_masks: 2
mask_feature_prob: 0.0
mask_feature_length: 10
mask_feature_min_masks: 0
max_new_tokens: 444
generation_config:
  alignment_heads: null
  begin_suppress_tokens: [220, 50256]
  bos_token_id: 50257
  decoder_start_token_id: 50258
  eos_token_id: 50257
  is_multilingual: True
  task: transcribe
  language: fa
  lang_to_id:
    <|af|>: 50327
    <|am|>: 50334
    <|ar|>: 50272
    <|as|>: 50350
    <|az|>: 50304
    <|ba|>: 50355
    <|be|>: 50330
    <|bg|>: 50292
    <|bn|>: 50302
    <|bo|>: 50347
    <|br|>: 50309
    <|bs|>: 50315
    <|ca|>: 50270
    <|cs|>: 50283
    <|cy|>: 50297
    <|da|>: 50285
    <|de|>: 50261
    <|el|>: 50281
    <|en|>: 50259
    <|es|>: 50262
    <|et|>: 50307
    <|eu|>: 50310
    <|fa|>: 50300
    <|fi|>: 50277
    <|fo|>: 50338
    <|fr|>: 50265
    <|gl|>: 50319
    <|gu|>: 50333
    <|haw|>: 50352
    <|ha|>: 50354
    <|he|>: 50279
    <|hi|>: 50276
    <|hr|>: 50291
    <|ht|>: 50339
    <|hu|>: 50286
    <|hy|>: 50312
    <|id|>: 50275
    <|is|>: 50311
    <|it|>: 50274
    <|ja|>: 50266
    <|jw|>: 50356
    <|ka|>: 50329
    <|kk|>: 50316
    <|km|>: 50323
    <|kn|>: 50306
    <|ko|>: 50264
    <|la|>: 50294
    <|lb|>: 50345
    <|ln|>: 50353
    <|lo|>: 50336
    <|lt|>: 50293
    <|lv|>: 50301
    <|mg|>: 50349
    <|mi|>: 50295
    <|mk|>: 50308
    <|ml|>: 50296
    <|mn|>: 50314
    <|mr|>: 50320
    <|ms|>: 50282
    <|mt|>: 50343
    <|my|>: 50346
    <|ne|>: 50313
    <|nl|>: 50271
    <|nn|>: 50342
    <|no|>: 50288
    <|oc|>: 50328
    <|pa|>: 50321
    <|pl|>: 50269
    <|ps|>: 50340
    <|pt|>: 50267
    <|ro|>: 50284
    <|ru|>: 50263
    <|sa|>: 50344
    <|sd|>: 50332
    <|si|>: 50322
    <|sk|>: 50298
    <|sl|>: 50305
    <|sn|>: 50324
    <|so|>: 50326
    <|sq|>: 50317
    <|sr|>: 50303
    <|su|>: 50357
    <|sv|>: 50273
    <|sw|>: 50318
    <|ta|>: 50287
    <|te|>: 50299
    <|tg|>: 50331
    <|th|>: 50289
    <|tk|>: 50341
    <|tl|>: 50348
    <|tr|>: 50268
    <|tt|>: 50351
    <|uk|>: 50280
    <|ur|>: 50290
    <|uz|>: 50337
    <|vi|>: 50278
    <|yi|>: 50335
    <|yo|>: 50325
    <|zh|>: 50260
  max_initial_timestamp_index: 50
  max_length: 448
  no_timestamps_token_id: 50363
  pad_token_id: 50257
  prev_sot_token_id: 50361
  return_timestamps: false
  suppress_tokens: null 
  task_to_id:
    transcribe: 50359
    translate: 50358