Hugging Face's logo

mlx-community
/
chatterbox-turbo-8bit

Text-to-Speech
Safetensors
MLX
English
mlx-audio
chatterbox_turbo
speech
speech generation
voice cloning
tts
8-bit precision
Model card Files
xet
 Community
prince-canuma commited on
Commit
6b1ed6c
·
verified ·
1 Parent(s): 098ef1e

Upload folder using huggingface_hub

Browse files
Files changed (10) hide show
  1. README.md +29 -0
  2. added_tokens.json +21 -0
  3. conds.safetensors +3 -0
  4. config.json +91 -0
  5. merges.txt +0 -0
  6. model.safetensors +3 -0
  7. model.safetensors.index.json +0 -0
  8. special_tokens_map.json +24 -0
  9. tokenizer_config.json +175 -0
  10. vocab.json +0 -0
README.md ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ language:
4
+ - en
5
+ base_model:
6
+ - mlx-community/chatterbox-turbo
7
+ pipeline_tag: text-to-speech
8
+ library_name: mlx-audio
9
+ tags:
10
+ - text-to-speech
11
+ - speech
12
+ - speech generation
13
+ - voice cloning
14
+ - mlx
15
+ - mlx
16
+ ---
17
+
18
+ # mlx-community/chatterbox-turbo-8bit
19
+ This model was converted to MLX format from [`mlx-community/chatterbox-turbo`](https://huggingface.co/mlx-community/chatterbox-turbo) using mlx-audio version **0.2.7**.
20
+ Refer to the [original model card](https://huggingface.co/mlx-community/chatterbox-turbo) for more details on the model.
21
+ ## Use with mlx
22
+
23
+ ```bash
24
+ pip install -U mlx-audio
25
+ ```
26
+
27
+ ```bash
28
+ python -m mlx_audio.tts.generate --model mlx-community/chatterbox-turbo-8bit --text "Describe this image."
29
+ ```
added_tokens.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "[advertisement]": 50261,
3
+ "[angry]": 50257,
4
+ "[chuckle]": 50274,
5
+ "[clear throat]": 50267,
6
+ "[cough]": 50270,
7
+ "[crying]": 50264,
8
+ "[dramatic]": 50262,
9
+ "[fear]": 50258,
10
+ "[gasp]": 50273,
11
+ "[groan]": 50271,
12
+ "[happy]": 50265,
13
+ "[laugh]": 50275,
14
+ "[narration]": 50263,
15
+ "[sarcastic]": 50266,
16
+ "[shush]": 50269,
17
+ "[sigh]": 50268,
18
+ "[sniff]": 50272,
19
+ "[surprised]": 50259,
20
+ "[whispering]": 50260
21
+ }
conds.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:df9ad2c54848027d94cf01f9fc0ed22bc5d3165df6e6a85c903c1124b8a78a4a
3
+ size 164884
config.json ADDED
@@ -0,0 +1,91 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architecture": "chatterbox_turbo",
3
+ "dec_cond_len_seconds": 10,
4
+ "enc_cond_len_seconds": 15,
5
+ "gpt2": {
6
+ "activation_function": "gelu_new",
7
+ "n_ctx": 8196,
8
+ "n_embd": 1024,
9
+ "hidden_size": 1024,
10
+ "n_head": 16,
11
+ "n_layer": 24,
12
+ "n_positions": 8196,
13
+ "vocab_size": 50276,
14
+ "layer_norm_epsilon": 1e-05,
15
+ "attn_pdrop": 0.1,
16
+ "embd_pdrop": 0.1,
17
+ "resid_pdrop": 0.1
18
+ },
19
+ "model_type": "chatterbox_turbo",
20
+ "quantization": {
21
+ "group_size": 64,
22
+ "bits": 8,
23
+ "mode": "affine"
24
+ },
25
+ "quantization_config": {
26
+ "group_size": 64,
27
+ "bits": 8,
28
+ "mode": "affine"
29
+ },
30
+ "s3gen": {
31
+ "output_sample_rate": 24000,
32
+ "input_sample_rate": 16000,
33
+ "silence_token": 4299,
34
+ "speech_vocab_size": 6561,
35
+ "meanflow": true,
36
+ "token_embedding_dim": 512,
37
+ "encoder_attention_heads": 8,
38
+ "encoder_linear_units": 2048,
39
+ "encoder_num_blocks": 6,
40
+ "encoder_dropout_rate": 0.1,
41
+ "decoder_in_channels": 320,
42
+ "decoder_out_channels": 80,
43
+ "decoder_channels": [
44
+ 256
45
+ ],
46
+ "decoder_attention_head_dim": 64,
47
+ "decoder_n_blocks": 4,
48
+ "decoder_num_mid_blocks": 12,
49
+ "decoder_num_heads": 8,
50
+ "cfm_sigma_min": 1e-06,
51
+ "cfm_t_scheduler": "cosine",
52
+ "cfm_inference_cfg_rate": 0.7
53
+ },
54
+ "sample_rate": 24000,
55
+ "t3": {
56
+ "start_text_token": 255,
57
+ "stop_text_token": 0,
58
+ "text_tokens_dict_size": 50276,
59
+ "max_text_tokens": 2048,
60
+ "start_speech_token": 6561,
61
+ "stop_speech_token": 6562,
62
+ "speech_tokens_dict_size": 6563,
63
+ "max_speech_tokens": 4096,
64
+ "llama_config_name": "GPT2_medium",
65
+ "input_pos_emb": null,
66
+ "speech_cond_prompt_len": 375,
67
+ "encoder_type": "voice_encoder",
68
+ "speaker_embed_size": 256,
69
+ "use_perceiver_resampler": false,
70
+ "emotion_adv": false
71
+ },
72
+ "voice_encoder": {
73
+ "num_mels": 40,
74
+ "sample_rate": 16000,
75
+ "speaker_embed_size": 256,
76
+ "ve_hidden_size": 256,
77
+ "flatten_lstm_params": false,
78
+ "n_fft": 400,
79
+ "hop_size": 160,
80
+ "win_size": 400,
81
+ "fmax": 8000,
82
+ "fmin": 0,
83
+ "preemphasis": 0.0,
84
+ "mel_power": 2.0,
85
+ "mel_type": "amp",
86
+ "normalized_mels": false,
87
+ "ve_partial_frames": 160,
88
+ "ve_final_relu": true,
89
+ "stft_magnitude_min": 0.0001
90
+ }
91
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cbfe447b04d11bb2d877f1305c37945ca109ffcf74a982a533e4baa40f273ba2
3
+ size 706233417
model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff
 
special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|endoftext|>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|endoftext|>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "<|endoftext|>",
17
+ "unk_token": {
18
+ "content": "<|endoftext|>",
19
+ "lstrip": false,
20
+ "normalized": true,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,175 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "50256": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": true,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "50257": {
14
+ "content": "[angry]",
15
+ "lstrip": false,
16
+ "normalized": true,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": false
20
+ },
21
+ "50258": {
22
+ "content": "[fear]",
23
+ "lstrip": false,
24
+ "normalized": true,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": false
28
+ },
29
+ "50259": {
30
+ "content": "[surprised]",
31
+ "lstrip": false,
32
+ "normalized": true,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": false
36
+ },
37
+ "50260": {
38
+ "content": "[whispering]",
39
+ "lstrip": false,
40
+ "normalized": true,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": false
44
+ },
45
+ "50261": {
46
+ "content": "[advertisement]",
47
+ "lstrip": false,
48
+ "normalized": true,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": false
52
+ },
53
+ "50262": {
54
+ "content": "[dramatic]",
55
+ "lstrip": false,
56
+ "normalized": true,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": false
60
+ },
61
+ "50263": {
62
+ "content": "[narration]",
63
+ "lstrip": false,
64
+ "normalized": true,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": false
68
+ },
69
+ "50264": {
70
+ "content": "[crying]",
71
+ "lstrip": false,
72
+ "normalized": true,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": false
76
+ },
77
+ "50265": {
78
+ "content": "[happy]",
79
+ "lstrip": false,
80
+ "normalized": true,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": false
84
+ },
85
+ "50266": {
86
+ "content": "[sarcastic]",
87
+ "lstrip": false,
88
+ "normalized": true,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": false
92
+ },
93
+ "50267": {
94
+ "content": "[clear throat]",
95
+ "lstrip": false,
96
+ "normalized": true,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": false
100
+ },
101
+ "50268": {
102
+ "content": "[sigh]",
103
+ "lstrip": false,
104
+ "normalized": true,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": false
108
+ },
109
+ "50269": {
110
+ "content": "[shush]",
111
+ "lstrip": false,
112
+ "normalized": true,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": false
116
+ },
117
+ "50270": {
118
+ "content": "[cough]",
119
+ "lstrip": false,
120
+ "normalized": true,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": false
124
+ },
125
+ "50271": {
126
+ "content": "[groan]",
127
+ "lstrip": false,
128
+ "normalized": true,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": false
132
+ },
133
+ "50272": {
134
+ "content": "[sniff]",
135
+ "lstrip": false,
136
+ "normalized": true,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": false
140
+ },
141
+ "50273": {
142
+ "content": "[gasp]",
143
+ "lstrip": false,
144
+ "normalized": true,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": false
148
+ },
149
+ "50274": {
150
+ "content": "[chuckle]",
151
+ "lstrip": false,
152
+ "normalized": true,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": false
156
+ },
157
+ "50275": {
158
+ "content": "[laugh]",
159
+ "lstrip": false,
160
+ "normalized": true,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": false
164
+ }
165
+ },
166
+ "bos_token": "<|endoftext|>",
167
+ "clean_up_tokenization_spaces": false,
168
+ "eos_token": "<|endoftext|>",
169
+ "errors": "replace",
170
+ "extra_special_tokens": {},
171
+ "model_max_length": 1024,
172
+ "pad_token": "<|endoftext|>",
173
+ "tokenizer_class": "GPT2Tokenizer",
174
+ "unk_token": "<|endoftext|>"
175
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff