Hugging Face's logo

ddwang2000
/
EchoChat

Text Generation
Transformers
Safetensors
English
qwen2
audio
speech
conversational
custom_code
text-generation-inference
Model card Files
xet
 Community
EchoChat
File size: 2,441 Bytes
b6d2bc8
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
{
  "vocab_size": 51866,
  "num_mel_bins": 128,
  "d_model": 1280,
  "encoder_layers": 32,
  "encoder_attention_heads": 20,
  "decoder_layers": 32,
  "decoder_attention_heads": 20,
  "decoder_ffn_dim": 5120,
  "encoder_ffn_dim": 5120,
  "dropout": 0.0,
  "attention_dropout": 0.0,
  "activation_dropout": 0.0,
  "activation_function": "gelu",
  "init_std": 0.02,
  "encoder_layerdrop": 0.0,
  "decoder_layerdrop": 0.0,
  "use_cache": true,
  "num_hidden_layers": 32,
  "scale_embedding": false,
  "max_source_positions": 1500,
  "max_target_positions": 448,
  "classifier_proj_size": 256,
  "use_weighted_layer_sum": false,
  "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,
  "median_filter_width": 7,
  "return_dict": true,
  "output_hidden_states": false,
  "output_attentions": false,
  "torchscript": false,
  "torch_dtype": "bfloat16",
  "use_bfloat16": false,
  "tf_legacy_loss": false,
  "pruned_heads": {},
  "tie_word_embeddings": true,
  "chunk_size_feed_forward": 0,
  "is_encoder_decoder": true,
  "is_decoder": false,
  "cross_attention_hidden_size": null,
  "add_cross_attention": false,
  "tie_encoder_decoder": false,
  "max_length": 448,
  "min_length": 0,
  "do_sample": false,
  "early_stopping": false,
  "num_beams": 1,
  "num_beam_groups": 1,
  "diversity_penalty": 0.0,
  "temperature": 1.0,
  "top_k": 50,
  "top_p": 1.0,
  "typical_p": 1.0,
  "repetition_penalty": 1.0,
  "length_penalty": 1.0,
  "no_repeat_ngram_size": 0,
  "encoder_no_repeat_ngram_size": 0,
  "bad_words_ids": null,
  "num_return_sequences": 1,
  "output_scores": false,
  "return_dict_in_generate": false,
  "forced_bos_token_id": null,
  "forced_eos_token_id": null,
  "remove_invalid_values": false,
  "exponential_decay_length_penalty": null,
  "suppress_tokens": null,
  "begin_suppress_tokens": [
    220,
    50257
  ],
  "architectures": [
    "WhisperEncoder"
  ],
  "id2label": {
    "0": "LABEL_0",
    "1": "LABEL_1"
  },
  "label2id": {
    "LABEL_0": 0,
    "LABEL_1": 1
  },
  "tokenizer_class": null,
  "prefix": null,
  "bos_token_id": 50257,
  "pad_token_id": 50256,
  "eos_token_id": 50257,
  "sep_token_id": null,
  "decoder_start_token_id": 50258,
  "problem_type": null,
  "_attn_implementation_autoset": true,
  "transformers_version": "4.51.3",
  "model_type": "whisper"
}