Hugging Face's logo

guanwenhao
/
MonoSpeech

Any-to-Any
Transformers
English
audio
speech
tts
asr
unified_model
Inference Endpoints
Model card Files Community
root commited on
Commit
c719855
·
1 Parent(s): c5d20f1

upload monospeech_tts model

Browse files
Files changed (24) hide show
  1. monospeech_all/added_tokens.json +6 -0
  2. monospeech_all/config.json +51 -0
  3. monospeech_all/merges.txt +0 -0
  4. monospeech_all/pytorch_model.bin +3 -0
  5. monospeech_all/special_tokens_map.json +34 -0
  6. monospeech_all/tokenizer.json +0 -0
  7. monospeech_all/tokenizer_config.json +188 -0
  8. monospeech_all/vocab.json +0 -0
  9. monospeech_asr/added_tokens.json +6 -0
  10. monospeech_asr/config.json +51 -0
  11. monospeech_asr/merges.txt +0 -0
  12. monospeech_asr/pytorch_model.bin +3 -0
  13. monospeech_asr/special_tokens_map.json +34 -0
  14. monospeech_asr/tokenizer.json +0 -0
  15. monospeech_asr/tokenizer_config.json +188 -0
  16. monospeech_asr/vocab.json +0 -0
  17. monospeech_tts/added_tokens.json +6 -0
  18. monospeech_tts/config.json +51 -0
  19. monospeech_tts/merges.txt +0 -0
  20. monospeech_tts/pytorch_model.bin +3 -0
  21. monospeech_tts/special_tokens_map.json +34 -0
  22. monospeech_tts/tokenizer.json +0 -0
  23. monospeech_tts/tokenizer_config.json +188 -0
  24. monospeech_tts/vocab.json +0 -0
monospeech_all/added_tokens.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "<PAD>": 49152,
3
+ "<SPEECH>": 49153,
4
+ "<|speech_end|>": 49155,
5
+ "<|speech_start|>": 49154
6
+ }
monospeech_all/config.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "hf_ckpts/SmolLM2-360M-Instruct",
3
+ "add_pos_embed_each_layer": false,
4
+ "architectures": [
5
+ "LlamaForCausalLM"
6
+ ],
7
+ "attention_bias": false,
8
+ "attention_dropout": 0.0,
9
+ "attn_implementation": "eager",
10
+ "audio_encoder_path": "hf_ckpts/whisper-large-v3",
11
+ "bos_token_id": 1,
12
+ "decoder_t_embed": "add_before_speech_tokens",
13
+ "eos_token_id": 2,
14
+ "hidden_act": "silu",
15
+ "hidden_size": 960,
16
+ "initializer_range": 0.02,
17
+ "intermediate_size": 2560,
18
+ "is_llama_config": true,
19
+ "learn_sigma": true,
20
+ "max_position_embeddings": 8192,
21
+ "mlp_bias": false,
22
+ "model_type": "llama",
23
+ "num_attention_heads": 15,
24
+ "num_hidden_layers": 32,
25
+ "num_key_value_heads": 5,
26
+ "pad_token_id": 2,
27
+ "pretraining_tp": 1,
28
+ "rms_norm_eps": 1e-05,
29
+ "rope_interleaved": false,
30
+ "rope_scaling": null,
31
+ "rope_theta": 100000,
32
+ "speaker_encoder_path": "hf_ckpts/wav2vec2-large-xlsr-53",
33
+ "tie_word_embeddings": true,
34
+ "tokenizer_max_length": 1024,
35
+ "tokenizer_padding_side": "right",
36
+ "torch_dtype": "bfloat16",
37
+ "transformers.js_config": {
38
+ "kv_cache_dtype": {
39
+ "fp16": "float16",
40
+ "q4f16": "float16"
41
+ }
42
+ },
43
+ "transformers_version": "4.39.0",
44
+ "use_adaln_final_layer": true,
45
+ "use_bi_attn_speech_tokens": true,
46
+ "use_cache": true,
47
+ "use_flash_attn": false,
48
+ "use_hybrid_attn_mask": false,
49
+ "use_pos_embed": true,
50
+ "vocab_size": 49152
51
+ }
monospeech_all/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
monospeech_all/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:820548f895d8bffa87c38e0d8ee500f970ab85f1f8d0653b077d581361eeb929
3
+ size 5294465371
monospeech_all/special_tokens_map.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>"
5
+ ],
6
+ "bos_token": {
7
+ "content": "<|im_start|>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false
12
+ },
13
+ "eos_token": {
14
+ "content": "<|im_end|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false
19
+ },
20
+ "pad_token": {
21
+ "content": "<PAD>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false
26
+ },
27
+ "unk_token": {
28
+ "content": "<|endoftext|>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false
33
+ }
34
+ }
monospeech_all/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
monospeech_all/tokenizer_config.json ADDED
@@ -0,0 +1,188 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": true,
4
+ "add_prefix_space": false,
5
+ "added_tokens_decoder": {
6
+ "0": {
7
+ "content": "<|endoftext|>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": true
13
+ },
14
+ "1": {
15
+ "content": "<|im_start|>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": true
21
+ },
22
+ "2": {
23
+ "content": "<|im_end|>",
24
+ "lstrip": false,
25
+ "normalized": false,
26
+ "rstrip": false,
27
+ "single_word": false,
28
+ "special": true
29
+ },
30
+ "3": {
31
+ "content": "<repo_name>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false,
36
+ "special": true
37
+ },
38
+ "4": {
39
+ "content": "<reponame>",
40
+ "lstrip": false,
41
+ "normalized": false,
42
+ "rstrip": false,
43
+ "single_word": false,
44
+ "special": true
45
+ },
46
+ "5": {
47
+ "content": "<file_sep>",
48
+ "lstrip": false,
49
+ "normalized": false,
50
+ "rstrip": false,
51
+ "single_word": false,
52
+ "special": true
53
+ },
54
+ "6": {
55
+ "content": "<filename>",
56
+ "lstrip": false,
57
+ "normalized": false,
58
+ "rstrip": false,
59
+ "single_word": false,
60
+ "special": true
61
+ },
62
+ "7": {
63
+ "content": "<gh_stars>",
64
+ "lstrip": false,
65
+ "normalized": false,
66
+ "rstrip": false,
67
+ "single_word": false,
68
+ "special": true
69
+ },
70
+ "8": {
71
+ "content": "<issue_start>",
72
+ "lstrip": false,
73
+ "normalized": false,
74
+ "rstrip": false,
75
+ "single_word": false,
76
+ "special": true
77
+ },
78
+ "9": {
79
+ "content": "<issue_comment>",
80
+ "lstrip": false,
81
+ "normalized": false,
82
+ "rstrip": false,
83
+ "single_word": false,
84
+ "special": true
85
+ },
86
+ "10": {
87
+ "content": "<issue_closed>",
88
+ "lstrip": false,
89
+ "normalized": false,
90
+ "rstrip": false,
91
+ "single_word": false,
92
+ "special": true
93
+ },
94
+ "11": {
95
+ "content": "<jupyter_start>",
96
+ "lstrip": false,
97
+ "normalized": false,
98
+ "rstrip": false,
99
+ "single_word": false,
100
+ "special": true
101
+ },
102
+ "12": {
103
+ "content": "<jupyter_text>",
104
+ "lstrip": false,
105
+ "normalized": false,
106
+ "rstrip": false,
107
+ "single_word": false,
108
+ "special": true
109
+ },
110
+ "13": {
111
+ "content": "<jupyter_code>",
112
+ "lstrip": false,
113
+ "normalized": false,
114
+ "rstrip": false,
115
+ "single_word": false,
116
+ "special": true
117
+ },
118
+ "14": {
119
+ "content": "<jupyter_output>",
120
+ "lstrip": false,
121
+ "normalized": false,
122
+ "rstrip": false,
123
+ "single_word": false,
124
+ "special": true
125
+ },
126
+ "15": {
127
+ "content": "<jupyter_script>",
128
+ "lstrip": false,
129
+ "normalized": false,
130
+ "rstrip": false,
131
+ "single_word": false,
132
+ "special": true
133
+ },
134
+ "16": {
135
+ "content": "<empty_output>",
136
+ "lstrip": false,
137
+ "normalized": false,
138
+ "rstrip": false,
139
+ "single_word": false,
140
+ "special": true
141
+ },
142
+ "49152": {
143
+ "content": "<PAD>",
144
+ "lstrip": false,
145
+ "normalized": false,
146
+ "rstrip": false,
147
+ "single_word": false,
148
+ "special": true
149
+ },
150
+ "49153": {
151
+ "content": "<SPEECH>",
152
+ "lstrip": false,
153
+ "normalized": false,
154
+ "rstrip": false,
155
+ "single_word": false,
156
+ "special": true
157
+ },
158
+ "49154": {
159
+ "content": "<|speech_start|>",
160
+ "lstrip": false,
161
+ "normalized": false,
162
+ "rstrip": false,
163
+ "single_word": false,
164
+ "special": true
165
+ },
166
+ "49155": {
167
+ "content": "<|speech_end|>",
168
+ "lstrip": false,
169
+ "normalized": false,
170
+ "rstrip": false,
171
+ "single_word": false,
172
+ "special": true
173
+ }
174
+ },
175
+ "additional_special_tokens": [
176
+ "<|im_start|>",
177
+ "<|im_end|>"
178
+ ],
179
+ "bos_token": "<|im_start|>",
180
+ "chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful AI assistant named SmolLM, trained by Hugging Face<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
181
+ "clean_up_tokenization_spaces": false,
182
+ "eos_token": "<|im_end|>",
183
+ "model_max_length": 8192,
184
+ "pad_token": "<PAD>",
185
+ "tokenizer_class": "GPT2Tokenizer",
186
+ "unk_token": "<|endoftext|>",
187
+ "vocab_size": 49152
188
+ }
monospeech_all/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
monospeech_asr/added_tokens.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "<PAD>": 49152,
3
+ "<SPEECH>": 49153,
4
+ "<|speech_end|>": 49155,
5
+ "<|speech_start|>": 49154
6
+ }
monospeech_asr/config.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "hf_ckpts/SmolLM2-360M-Instruct",
3
+ "add_pos_embed_each_layer": false,
4
+ "architectures": [
5
+ "LlamaForCausalLM"
6
+ ],
7
+ "attention_bias": false,
8
+ "attention_dropout": 0.0,
9
+ "attn_implementation": "eager",
10
+ "audio_encoder_path": "whisper-large-v3",
11
+ "bos_token_id": 1,
12
+ "decoder_t_embed": "add_before_speech_tokens",
13
+ "eos_token_id": 2,
14
+ "hidden_act": "silu",
15
+ "hidden_size": 960,
16
+ "initializer_range": 0.02,
17
+ "intermediate_size": 2560,
18
+ "is_llama_config": true,
19
+ "learn_sigma": true,
20
+ "max_position_embeddings": 8192,
21
+ "mlp_bias": false,
22
+ "model_type": "llama",
23
+ "num_attention_heads": 15,
24
+ "num_hidden_layers": 32,
25
+ "num_key_value_heads": 5,
26
+ "pad_token_id": 2,
27
+ "pretraining_tp": 1,
28
+ "rms_norm_eps": 1e-05,
29
+ "rope_interleaved": false,
30
+ "rope_scaling": null,
31
+ "rope_theta": 100000,
32
+ "speaker_encoder_path": "hf_ckpts/wav2vec2-large-xlsr-53",
33
+ "tie_word_embeddings": true,
34
+ "tokenizer_max_length": 1024,
35
+ "tokenizer_padding_side": "right",
36
+ "torch_dtype": "bfloat16",
37
+ "transformers.js_config": {
38
+ "kv_cache_dtype": {
39
+ "fp16": "float16",
40
+ "q4f16": "float16"
41
+ }
42
+ },
43
+ "transformers_version": "4.39.0",
44
+ "use_adaln_final_layer": true,
45
+ "use_bi_attn_speech_tokens": true,
46
+ "use_cache": true,
47
+ "use_flash_attn": false,
48
+ "use_hybrid_attn_mask": false,
49
+ "use_pos_embed": true,
50
+ "vocab_size": 49152
51
+ }
monospeech_asr/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
monospeech_asr/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c09493a7971b1461c4fa510b983d0e8c0622f1eb8ae3a8330b037e633b7d07c
3
+ size 5294465371
monospeech_asr/special_tokens_map.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>"
5
+ ],
6
+ "bos_token": {
7
+ "content": "<|im_start|>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false
12
+ },
13
+ "eos_token": {
14
+ "content": "<|im_end|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false
19
+ },
20
+ "pad_token": {
21
+ "content": "<PAD>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false
26
+ },
27
+ "unk_token": {
28
+ "content": "<|endoftext|>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false
33
+ }
34
+ }
monospeech_asr/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
monospeech_asr/tokenizer_config.json ADDED
@@ -0,0 +1,188 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": true,
4
+ "add_prefix_space": false,
5
+ "added_tokens_decoder": {
6
+ "0": {
7
+ "content": "<|endoftext|>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": true
13
+ },
14
+ "1": {
15
+ "content": "<|im_start|>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": true
21
+ },
22
+ "2": {
23
+ "content": "<|im_end|>",
24
+ "lstrip": false,
25
+ "normalized": false,
26
+ "rstrip": false,
27
+ "single_word": false,
28
+ "special": true
29
+ },
30
+ "3": {
31
+ "content": "<repo_name>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false,
36
+ "special": true
37
+ },
38
+ "4": {
39
+ "content": "<reponame>",
40
+ "lstrip": false,
41
+ "normalized": false,
42
+ "rstrip": false,
43
+ "single_word": false,
44
+ "special": true
45
+ },
46
+ "5": {
47
+ "content": "<file_sep>",
48
+ "lstrip": false,
49
+ "normalized": false,
50
+ "rstrip": false,
51
+ "single_word": false,
52
+ "special": true
53
+ },
54
+ "6": {
55
+ "content": "<filename>",
56
+ "lstrip": false,
57
+ "normalized": false,
58
+ "rstrip": false,
59
+ "single_word": false,
60
+ "special": true
61
+ },
62
+ "7": {
63
+ "content": "<gh_stars>",
64
+ "lstrip": false,
65
+ "normalized": false,
66
+ "rstrip": false,
67
+ "single_word": false,
68
+ "special": true
69
+ },
70
+ "8": {
71
+ "content": "<issue_start>",
72
+ "lstrip": false,
73
+ "normalized": false,
74
+ "rstrip": false,
75
+ "single_word": false,
76
+ "special": true
77
+ },
78
+ "9": {
79
+ "content": "<issue_comment>",
80
+ "lstrip": false,
81
+ "normalized": false,
82
+ "rstrip": false,
83
+ "single_word": false,
84
+ "special": true
85
+ },
86
+ "10": {
87
+ "content": "<issue_closed>",
88
+ "lstrip": false,
89
+ "normalized": false,
90
+ "rstrip": false,
91
+ "single_word": false,
92
+ "special": true
93
+ },
94
+ "11": {
95
+ "content": "<jupyter_start>",
96
+ "lstrip": false,
97
+ "normalized": false,
98
+ "rstrip": false,
99
+ "single_word": false,
100
+ "special": true
101
+ },
102
+ "12": {
103
+ "content": "<jupyter_text>",
104
+ "lstrip": false,
105
+ "normalized": false,
106
+ "rstrip": false,
107
+ "single_word": false,
108
+ "special": true
109
+ },
110
+ "13": {
111
+ "content": "<jupyter_code>",
112
+ "lstrip": false,
113
+ "normalized": false,
114
+ "rstrip": false,
115
+ "single_word": false,
116
+ "special": true
117
+ },
118
+ "14": {
119
+ "content": "<jupyter_output>",
120
+ "lstrip": false,
121
+ "normalized": false,
122
+ "rstrip": false,
123
+ "single_word": false,
124
+ "special": true
125
+ },
126
+ "15": {
127
+ "content": "<jupyter_script>",
128
+ "lstrip": false,
129
+ "normalized": false,
130
+ "rstrip": false,
131
+ "single_word": false,
132
+ "special": true
133
+ },
134
+ "16": {
135
+ "content": "<empty_output>",
136
+ "lstrip": false,
137
+ "normalized": false,
138
+ "rstrip": false,
139
+ "single_word": false,
140
+ "special": true
141
+ },
142
+ "49152": {
143
+ "content": "<PAD>",
144
+ "lstrip": false,
145
+ "normalized": false,
146
+ "rstrip": false,
147
+ "single_word": false,
148
+ "special": true
149
+ },
150
+ "49153": {
151
+ "content": "<SPEECH>",
152
+ "lstrip": false,
153
+ "normalized": false,
154
+ "rstrip": false,
155
+ "single_word": false,
156
+ "special": true
157
+ },
158
+ "49154": {
159
+ "content": "<|speech_start|>",
160
+ "lstrip": false,
161
+ "normalized": false,
162
+ "rstrip": false,
163
+ "single_word": false,
164
+ "special": true
165
+ },
166
+ "49155": {
167
+ "content": "<|speech_end|>",
168
+ "lstrip": false,
169
+ "normalized": false,
170
+ "rstrip": false,
171
+ "single_word": false,
172
+ "special": true
173
+ }
174
+ },
175
+ "additional_special_tokens": [
176
+ "<|im_start|>",
177
+ "<|im_end|>"
178
+ ],
179
+ "bos_token": "<|im_start|>",
180
+ "chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful AI assistant named SmolLM, trained by Hugging Face<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
181
+ "clean_up_tokenization_spaces": false,
182
+ "eos_token": "<|im_end|>",
183
+ "model_max_length": 8192,
184
+ "pad_token": "<PAD>",
185
+ "tokenizer_class": "GPT2Tokenizer",
186
+ "unk_token": "<|endoftext|>",
187
+ "vocab_size": 49152
188
+ }
monospeech_asr/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
monospeech_tts/added_tokens.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "<PAD>": 49152,
3
+ "<SPEECH>": 49153,
4
+ "<|speech_end|>": 49155,
5
+ "<|speech_start|>": 49154
6
+ }
monospeech_tts/config.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "hf_ckpts/SmolLM2-360M-Instruct",
3
+ "add_pos_embed_each_layer": false,
4
+ "architectures": [
5
+ "LlamaForCausalLM"
6
+ ],
7
+ "attention_bias": false,
8
+ "attention_dropout": 0.0,
9
+ "attn_implementation": "eager",
10
+ "audio_encoder_path": "hf_ckpts/whisper-large-v3",
11
+ "bos_token_id": 1,
12
+ "decoder_t_embed": "add_before_speech_tokens",
13
+ "eos_token_id": 2,
14
+ "hidden_act": "silu",
15
+ "hidden_size": 960,
16
+ "initializer_range": 0.02,
17
+ "intermediate_size": 2560,
18
+ "is_llama_config": true,
19
+ "learn_sigma": true,
20
+ "max_position_embeddings": 8192,
21
+ "mlp_bias": false,
22
+ "model_type": "llama",
23
+ "num_attention_heads": 15,
24
+ "num_hidden_layers": 32,
25
+ "num_key_value_heads": 5,
26
+ "pad_token_id": 2,
27
+ "pretraining_tp": 1,
28
+ "rms_norm_eps": 1e-05,
29
+ "rope_interleaved": false,
30
+ "rope_scaling": null,
31
+ "rope_theta": 100000,
32
+ "speaker_encoder_path": "hf_ckpts/wav2vec2-large-xlsr-53",
33
+ "tie_word_embeddings": true,
34
+ "tokenizer_max_length": 1024,
35
+ "tokenizer_padding_side": "right",
36
+ "torch_dtype": "bfloat16",
37
+ "transformers.js_config": {
38
+ "kv_cache_dtype": {
39
+ "fp16": "float16",
40
+ "q4f16": "float16"
41
+ }
42
+ },
43
+ "transformers_version": "4.39.0",
44
+ "use_adaln_final_layer": true,
45
+ "use_bi_attn_speech_tokens": true,
46
+ "use_cache": true,
47
+ "use_flash_attn": false,
48
+ "use_hybrid_attn_mask": false,
49
+ "use_pos_embed": true,
50
+ "vocab_size": 49152
51
+ }
monospeech_tts/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
monospeech_tts/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:945b789bab04e81ddb55c1a4189667395a91ded69db9c42495f1ebbcff31b7c0
3
+ size 5294465371
monospeech_tts/special_tokens_map.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>"
5
+ ],
6
+ "bos_token": {
7
+ "content": "<|im_start|>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false
12
+ },
13
+ "eos_token": {
14
+ "content": "<|im_end|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false
19
+ },
20
+ "pad_token": {
21
+ "content": "<PAD>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false
26
+ },
27
+ "unk_token": {
28
+ "content": "<|endoftext|>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false
33
+ }
34
+ }
monospeech_tts/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
monospeech_tts/tokenizer_config.json ADDED
@@ -0,0 +1,188 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": true,
4
+ "add_prefix_space": false,
5
+ "added_tokens_decoder": {
6
+ "0": {
7
+ "content": "<|endoftext|>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": true
13
+ },
14
+ "1": {
15
+ "content": "<|im_start|>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": true
21
+ },
22
+ "2": {
23
+ "content": "<|im_end|>",
24
+ "lstrip": false,
25
+ "normalized": false,
26
+ "rstrip": false,
27
+ "single_word": false,
28
+ "special": true
29
+ },
30
+ "3": {
31
+ "content": "<repo_name>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false,
36
+ "special": true
37
+ },
38
+ "4": {
39
+ "content": "<reponame>",
40
+ "lstrip": false,
41
+ "normalized": false,
42
+ "rstrip": false,
43
+ "single_word": false,
44
+ "special": true
45
+ },
46
+ "5": {
47
+ "content": "<file_sep>",
48
+ "lstrip": false,
49
+ "normalized": false,
50
+ "rstrip": false,
51
+ "single_word": false,
52
+ "special": true
53
+ },
54
+ "6": {
55
+ "content": "<filename>",
56
+ "lstrip": false,
57
+ "normalized": false,
58
+ "rstrip": false,
59
+ "single_word": false,
60
+ "special": true
61
+ },
62
+ "7": {
63
+ "content": "<gh_stars>",
64
+ "lstrip": false,
65
+ "normalized": false,
66
+ "rstrip": false,
67
+ "single_word": false,
68
+ "special": true
69
+ },
70
+ "8": {
71
+ "content": "<issue_start>",
72
+ "lstrip": false,
73
+ "normalized": false,
74
+ "rstrip": false,
75
+ "single_word": false,
76
+ "special": true
77
+ },
78
+ "9": {
79
+ "content": "<issue_comment>",
80
+ "lstrip": false,
81
+ "normalized": false,
82
+ "rstrip": false,
83
+ "single_word": false,
84
+ "special": true
85
+ },
86
+ "10": {
87
+ "content": "<issue_closed>",
88
+ "lstrip": false,
89
+ "normalized": false,
90
+ "rstrip": false,
91
+ "single_word": false,
92
+ "special": true
93
+ },
94
+ "11": {
95
+ "content": "<jupyter_start>",
96
+ "lstrip": false,
97
+ "normalized": false,
98
+ "rstrip": false,
99
+ "single_word": false,
100
+ "special": true
101
+ },
102
+ "12": {
103
+ "content": "<jupyter_text>",
104
+ "lstrip": false,
105
+ "normalized": false,
106
+ "rstrip": false,
107
+ "single_word": false,
108
+ "special": true
109
+ },
110
+ "13": {
111
+ "content": "<jupyter_code>",
112
+ "lstrip": false,
113
+ "normalized": false,
114
+ "rstrip": false,
115
+ "single_word": false,
116
+ "special": true
117
+ },
118
+ "14": {
119
+ "content": "<jupyter_output>",
120
+ "lstrip": false,
121
+ "normalized": false,
122
+ "rstrip": false,
123
+ "single_word": false,
124
+ "special": true
125
+ },
126
+ "15": {
127
+ "content": "<jupyter_script>",
128
+ "lstrip": false,
129
+ "normalized": false,
130
+ "rstrip": false,
131
+ "single_word": false,
132
+ "special": true
133
+ },
134
+ "16": {
135
+ "content": "<empty_output>",
136
+ "lstrip": false,
137
+ "normalized": false,
138
+ "rstrip": false,
139
+ "single_word": false,
140
+ "special": true
141
+ },
142
+ "49152": {
143
+ "content": "<PAD>",
144
+ "lstrip": false,
145
+ "normalized": false,
146
+ "rstrip": false,
147
+ "single_word": false,
148
+ "special": true
149
+ },
150
+ "49153": {
151
+ "content": "<SPEECH>",
152
+ "lstrip": false,
153
+ "normalized": false,
154
+ "rstrip": false,
155
+ "single_word": false,
156
+ "special": true
157
+ },
158
+ "49154": {
159
+ "content": "<|speech_start|>",
160
+ "lstrip": false,
161
+ "normalized": false,
162
+ "rstrip": false,
163
+ "single_word": false,
164
+ "special": true
165
+ },
166
+ "49155": {
167
+ "content": "<|speech_end|>",
168
+ "lstrip": false,
169
+ "normalized": false,
170
+ "rstrip": false,
171
+ "single_word": false,
172
+ "special": true
173
+ }
174
+ },
175
+ "additional_special_tokens": [
176
+ "<|im_start|>",
177
+ "<|im_end|>"
178
+ ],
179
+ "bos_token": "<|im_start|>",
180
+ "chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful AI assistant named SmolLM, trained by Hugging Face<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
181
+ "clean_up_tokenization_spaces": false,
182
+ "eos_token": "<|im_end|>",
183
+ "model_max_length": 8192,
184
+ "pad_token": "<PAD>",
185
+ "tokenizer_class": "GPT2Tokenizer",
186
+ "unk_token": "<|endoftext|>",
187
+ "vocab_size": 49152
188
+ }
monospeech_tts/vocab.json ADDED
The diff for this file is too large to render. See raw diff