Hugging Face's logo

ylacombe
/
bark-small

Text-to-Speech
Transformers
PyTorch
13 languages
bark
text-to-audio
audio
Inference Endpoints
Model card Files Community
14
ylacombe HF staff commited on
Commit
b192d44
•
1 Parent(s): d6b20dd

Upload config

Browse files
Files changed (1) hide show
  1. generation_config.json +166 -0
generation_config.json ADDED
@@ -0,0 +1,166 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "coarse_acoustics_config": {
3
+ "_from_model_config": false,
4
+ "bad_words_ids": null,
5
+ "begin_suppress_tokens": null,
6
+ "bos_token_id": null,
7
+ "coarse_infer_token": 12050,
8
+ "coarse_rate_hz": 75,
9
+ "coarse_semantic_pad_token": 12048,
10
+ "constraints": null,
11
+ "decoder_start_token_id": null,
12
+ "diversity_penalty": 0.0,
13
+ "do_sample": true,
14
+ "early_stopping": false,
15
+ "encoder_no_repeat_ngram_size": 0,
16
+ "encoder_repetition_penalty": 1.0,
17
+ "eos_token_id": null,
18
+ "epsilon_cutoff": 0.0,
19
+ "eta_cutoff": 0.0,
20
+ "exponential_decay_length_penalty": null,
21
+ "force_words_ids": null,
22
+ "forced_bos_token_id": null,
23
+ "forced_decoder_ids": null,
24
+ "forced_eos_token_id": null,
25
+ "generation_kwargs": {},
26
+ "length_penalty": 1.0,
27
+ "max_coarse_history": 630,
28
+ "max_coarse_input_length": 256,
29
+ "max_length": 20,
30
+ "max_new_tokens": null,
31
+ "max_time": null,
32
+ "min_length": 0,
33
+ "min_new_tokens": null,
34
+ "n_coarse_codebooks": 2,
35
+ "no_repeat_ngram_size": 0,
36
+ "num_beam_groups": 1,
37
+ "num_beams": 1,
38
+ "num_return_sequences": 1,
39
+ "output_attentions": false,
40
+ "output_hidden_states": false,
41
+ "output_scores": false,
42
+ "pad_token_id": null,
43
+ "penalty_alpha": null,
44
+ "remove_invalid_values": false,
45
+ "renormalize_logits": true,
46
+ "repetition_penalty": 1.0,
47
+ "return_dict_in_generate": false,
48
+ "sliding_window_len": 60,
49
+ "suppress_tokens": null,
50
+ "temperature": 0.7,
51
+ "top_k": 50,
52
+ "top_p": 1.0,
53
+ "transformers_version": "4.31.0.dev0",
54
+ "typical_p": 1.0,
55
+ "use_cache": true
56
+ },
57
+ "codebook_size": 1024,
58
+ "fine_acoustics_config": {
59
+ "_from_model_config": false,
60
+ "bad_words_ids": null,
61
+ "begin_suppress_tokens": null,
62
+ "bos_token_id": null,
63
+ "constraints": null,
64
+ "decoder_start_token_id": null,
65
+ "diversity_penalty": 0.0,
66
+ "do_sample": false,
67
+ "early_stopping": false,
68
+ "encoder_no_repeat_ngram_size": 0,
69
+ "encoder_repetition_penalty": 1.0,
70
+ "eos_token_id": null,
71
+ "epsilon_cutoff": 0.0,
72
+ "eta_cutoff": 0.0,
73
+ "exponential_decay_length_penalty": null,
74
+ "force_words_ids": null,
75
+ "forced_bos_token_id": null,
76
+ "forced_decoder_ids": null,
77
+ "forced_eos_token_id": null,
78
+ "generation_kwargs": {},
79
+ "length_penalty": 1.0,
80
+ "max_fine_history_length": 512,
81
+ "max_fine_input_length": 1024,
82
+ "max_length": 20,
83
+ "max_new_tokens": null,
84
+ "max_time": null,
85
+ "min_length": 0,
86
+ "min_new_tokens": null,
87
+ "n_fine_codebooks": 8,
88
+ "no_repeat_ngram_size": 0,
89
+ "num_beam_groups": 1,
90
+ "num_beams": 1,
91
+ "num_return_sequences": 1,
92
+ "output_attentions": false,
93
+ "output_hidden_states": false,
94
+ "output_scores": false,
95
+ "pad_token_id": null,
96
+ "penalty_alpha": null,
97
+ "remove_invalid_values": false,
98
+ "renormalize_logits": false,
99
+ "repetition_penalty": 1.0,
100
+ "return_dict_in_generate": false,
101
+ "suppress_tokens": null,
102
+ "temperature": 0.5,
103
+ "top_k": 50,
104
+ "top_p": 1.0,
105
+ "transformers_version": "4.31.0.dev0",
106
+ "typical_p": 1.0,
107
+ "use_cache": true
108
+ },
109
+ "model_type": "bark",
110
+ "sample_rate": 24000,
111
+ "semantic_config": {
112
+ "_from_model_config": false,
113
+ "bad_words_ids": null,
114
+ "begin_suppress_tokens": null,
115
+ "bos_token_id": null,
116
+ "constraints": null,
117
+ "decoder_start_token_id": null,
118
+ "diversity_penalty": 0.0,
119
+ "do_sample": true,
120
+ "early_stopping": false,
121
+ "encoder_no_repeat_ngram_size": 0,
122
+ "encoder_repetition_penalty": 1.0,
123
+ "eos_token_id": 10000,
124
+ "epsilon_cutoff": 0.0,
125
+ "eta_cutoff": 0.0,
126
+ "exponential_decay_length_penalty": null,
127
+ "force_words_ids": null,
128
+ "forced_bos_token_id": null,
129
+ "forced_decoder_ids": null,
130
+ "forced_eos_token_id": null,
131
+ "generation_kwargs": {},
132
+ "length_penalty": 1.0,
133
+ "max_input_semantic_length": 256,
134
+ "max_length": 20,
135
+ "max_new_tokens": 768,
136
+ "max_time": null,
137
+ "min_length": 0,
138
+ "min_new_tokens": null,
139
+ "no_repeat_ngram_size": 0,
140
+ "num_beam_groups": 1,
141
+ "num_beams": 1,
142
+ "num_return_sequences": 1,
143
+ "output_attentions": false,
144
+ "output_hidden_states": false,
145
+ "output_scores": false,
146
+ "pad_token_id": null,
147
+ "penalty_alpha": null,
148
+ "remove_invalid_values": false,
149
+ "renormalize_logits": true,
150
+ "repetition_penalty": 1.0,
151
+ "return_dict_in_generate": false,
152
+ "semantic_infer_token": 129599,
153
+ "semantic_pad_token": 10000,
154
+ "semantic_rate_hz": 49.9,
155
+ "semantic_vocab_size": 10000,
156
+ "suppress_tokens": null,
157
+ "temperature": 0.7,
158
+ "text_encoding_offset": 10048,
159
+ "text_pad_token": 129595,
160
+ "top_k": 50,
161
+ "top_p": 1.0,
162
+ "transformers_version": "4.31.0.dev0",
163
+ "typical_p": 1.0,
164
+ "use_cache": true
165
+ }
166
+ }