speech_encoder/encoder_config.json

{
  "_attn_implementation_autoset": true,
  "_name_or_path": "/data/projects/13003558/lewiswon/models/meralion_whisper_v3_normed_cleaned",
  "activation_dropout": 0.0,
  "activation_function": "gelu",
  "apply_spec_augment": true,
  "architectures": [
    "WhisperForConditionalGeneration"
  ],
  "attention_dropout": 0.0,
  "begin_suppress_tokens": null,
  "bos_token_id": 50257,
  "classifier_proj_size": 256,
  "d_model": 1280,
  "decoder_attention_heads": 20,
  "decoder_ffn_dim": 5120,
  "decoder_layerdrop": 0.0,
  "decoder_layers": 32,
  "decoder_start_token_id": 50258,
  "dropout": 0.0,
  "encoder_attention_heads": 20,
  "encoder_ffn_dim": 5120,
  "encoder_layerdrop": 0.0,
  "encoder_layers": 32,
  "eos_token_id": 50257,
  "init_std": 0.02,
  "mask_feature_length": 10,
  "mask_feature_min_masks": 0,
  "mask_feature_prob": 0.1,
  "mask_time_length": 20,
  "mask_time_min_masks": 2,
  "mask_time_prob": 0.1,
  "max_length": null,
  "max_source_positions": 1500,
  "max_target_positions": 448,
  "median_filter_width": 7,
  "model_type": "whisper",
  "num_hidden_layers": 32,
  "num_mel_bins": 128,
  "scale_embedding": false,
  "torch_dtype": "bfloat16",
  "use_cache": true,
  "use_weighted_layer_sum": true,
  "vocab_size": 51866
}