|
{ |
|
"_attn_implementation_autoset": true, |
|
"_name_or_path": "efficient-speech/lite-whisper-large-v3-fast", |
|
"activation_dropout": 0.0, |
|
"activation_function": "gelu", |
|
"apply_spec_augment": false, |
|
"architectures": [ |
|
"LiteWhisperForConditionalGeneration" |
|
], |
|
"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, |
|
"is_encoder_decoder": true, |
|
"low_rank_config": [ |
|
{ |
|
"fc1": 320, |
|
"fc2": 272, |
|
"k_proj": 32, |
|
"out_proj": 32, |
|
"q_proj": 32, |
|
"v_proj": 48 |
|
}, |
|
{ |
|
"fc1": 192, |
|
"fc2": 224, |
|
"k_proj": 64, |
|
"out_proj": 112, |
|
"q_proj": 64, |
|
"v_proj": 128 |
|
}, |
|
{ |
|
"fc1": 128, |
|
"fc2": 112, |
|
"k_proj": 48, |
|
"out_proj": 160, |
|
"q_proj": 48, |
|
"v_proj": 160 |
|
}, |
|
{ |
|
"fc1": 192, |
|
"fc2": 96, |
|
"k_proj": 48, |
|
"out_proj": 160, |
|
"q_proj": 48, |
|
"v_proj": 192 |
|
}, |
|
{ |
|
"fc1": 192, |
|
"fc2": 160, |
|
"k_proj": 48, |
|
"out_proj": 144, |
|
"q_proj": 64, |
|
"v_proj": 208 |
|
}, |
|
{ |
|
"fc1": 192, |
|
"fc2": 160, |
|
"k_proj": 48, |
|
"out_proj": 144, |
|
"q_proj": 48, |
|
"v_proj": 192 |
|
}, |
|
{ |
|
"fc1": 224, |
|
"fc2": 224, |
|
"k_proj": 64, |
|
"out_proj": 208, |
|
"q_proj": 80, |
|
"v_proj": 304 |
|
}, |
|
{ |
|
"fc1": 240, |
|
"fc2": 432, |
|
"k_proj": 80, |
|
"out_proj": 208, |
|
"q_proj": 96, |
|
"v_proj": 256 |
|
}, |
|
{ |
|
"fc1": 288, |
|
"fc2": 512, |
|
"k_proj": 80, |
|
"out_proj": 224, |
|
"q_proj": 96, |
|
"v_proj": 288 |
|
}, |
|
{ |
|
"fc1": 288, |
|
"fc2": 512, |
|
"k_proj": 80, |
|
"out_proj": 224, |
|
"q_proj": 96, |
|
"v_proj": 288 |
|
}, |
|
{ |
|
"fc1": 320, |
|
"fc2": 528, |
|
"k_proj": 48, |
|
"out_proj": 240, |
|
"q_proj": 64, |
|
"v_proj": 288 |
|
}, |
|
{ |
|
"fc1": 320, |
|
"fc2": 528, |
|
"k_proj": 64, |
|
"out_proj": 224, |
|
"q_proj": 80, |
|
"v_proj": 320 |
|
}, |
|
{ |
|
"fc1": 352, |
|
"fc2": 592, |
|
"k_proj": 64, |
|
"out_proj": 224, |
|
"q_proj": 64, |
|
"v_proj": 352 |
|
}, |
|
{ |
|
"fc1": 400, |
|
"fc2": 688, |
|
"k_proj": 48, |
|
"out_proj": 240, |
|
"q_proj": 64, |
|
"v_proj": 288 |
|
}, |
|
{ |
|
"fc1": 480, |
|
"fc2": 656, |
|
"k_proj": 64, |
|
"out_proj": 256, |
|
"q_proj": 80, |
|
"v_proj": 448 |
|
}, |
|
{ |
|
"fc1": 384, |
|
"fc2": 768, |
|
"k_proj": 48, |
|
"out_proj": 256, |
|
"q_proj": 48, |
|
"v_proj": 432 |
|
}, |
|
{ |
|
"fc1": 400, |
|
"fc2": 800, |
|
"k_proj": 48, |
|
"out_proj": 224, |
|
"q_proj": 64, |
|
"v_proj": 272 |
|
}, |
|
{ |
|
"fc1": 464, |
|
"fc2": 784, |
|
"k_proj": 80, |
|
"out_proj": 288, |
|
"q_proj": 96, |
|
"v_proj": 368 |
|
}, |
|
{ |
|
"fc1": 512, |
|
"fc2": 848, |
|
"k_proj": 64, |
|
"out_proj": 256, |
|
"q_proj": 80, |
|
"v_proj": 304 |
|
}, |
|
{ |
|
"fc1": 528, |
|
"fc2": 752, |
|
"k_proj": 80, |
|
"out_proj": 272, |
|
"q_proj": 80, |
|
"v_proj": 416 |
|
}, |
|
{ |
|
"fc1": 400, |
|
"fc2": 16, |
|
"k_proj": 80, |
|
"out_proj": 352, |
|
"q_proj": 96, |
|
"v_proj": 432 |
|
}, |
|
{ |
|
"fc1": 672, |
|
"fc2": 960, |
|
"k_proj": 96, |
|
"out_proj": 336, |
|
"q_proj": 112, |
|
"v_proj": 448 |
|
}, |
|
{ |
|
"fc1": 640, |
|
"fc2": 976, |
|
"k_proj": 112, |
|
"out_proj": 448, |
|
"q_proj": 144, |
|
"v_proj": 544 |
|
}, |
|
{ |
|
"fc1": 720, |
|
"k_proj": 96, |
|
"out_proj": 416, |
|
"q_proj": 128, |
|
"v_proj": 464 |
|
}, |
|
{ |
|
"fc1": 752, |
|
"k_proj": 128, |
|
"out_proj": 448, |
|
"q_proj": 176, |
|
"v_proj": 560 |
|
}, |
|
{ |
|
"fc1": 752, |
|
"k_proj": 128, |
|
"out_proj": 416, |
|
"q_proj": 176, |
|
"v_proj": 592 |
|
}, |
|
{ |
|
"fc1": 848, |
|
"k_proj": 144, |
|
"out_proj": 496, |
|
"q_proj": 192, |
|
"v_proj": 624 |
|
}, |
|
{ |
|
"fc1": 912, |
|
"fc2": 1024, |
|
"k_proj": 128, |
|
"out_proj": 400, |
|
"q_proj": 192, |
|
"v_proj": 608 |
|
}, |
|
{ |
|
"fc1": 944, |
|
"fc2": 944, |
|
"k_proj": 144, |
|
"out_proj": 448, |
|
"q_proj": 208, |
|
"v_proj": 592 |
|
}, |
|
{ |
|
"fc1": 960, |
|
"fc2": 976, |
|
"k_proj": 176, |
|
"out_proj": 496, |
|
"q_proj": 272, |
|
"v_proj": 560 |
|
}, |
|
{ |
|
"fc1": 896, |
|
"fc2": 992, |
|
"k_proj": 192, |
|
"out_proj": 464, |
|
"q_proj": 272, |
|
"v_proj": 560 |
|
}, |
|
{ |
|
"fc1": 800, |
|
"fc2": 736, |
|
"k_proj": 176, |
|
"out_proj": 464, |
|
"q_proj": 272, |
|
"v_proj": 432 |
|
} |
|
], |
|
"mask_feature_length": 10, |
|
"mask_feature_min_masks": 0, |
|
"mask_feature_prob": 0.0, |
|
"mask_time_length": 10, |
|
"mask_time_min_masks": 2, |
|
"mask_time_prob": 0.05, |
|
"max_length": null, |
|
"max_source_positions": 1500, |
|
"max_target_positions": 448, |
|
"median_filter_width": 7, |
|
"model_type": "lite-whisper", |
|
"num_hidden_layers": 32, |
|
"num_mel_bins": 128, |
|
"pad_token_id": 50256, |
|
"scale_embedding": false, |
|
"transformers_version": "4.48.3", |
|
"use_cache": true, |
|
"use_weighted_layer_sum": false, |
|
"vocab_size": 51866, |
|
"transformers.js_config": { |
|
"use_external_data_format": { |
|
"decoder_model.onnx": true, |
|
"decoder_model_merged.onnx": true, |
|
"decoder_with_past_model.onnx": true |
|
} |
|
} |
|
} |