ylacombe HF staff commited on
Commit
50d807f
0 Parent(s):

Duplicate from ylacombe/bark-small

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. .gitattributes +34 -0
  2. README.md +190 -0
  3. config.json +340 -0
  4. generation_config.json +172 -0
  5. pytorch_model.bin +3 -0
  6. speaker_embeddings/announcer_coarse_prompt.npy +3 -0
  7. speaker_embeddings/announcer_fine_prompt.npy +3 -0
  8. speaker_embeddings/announcer_semantic_prompt.npy +3 -0
  9. speaker_embeddings/de_speaker_0_coarse_prompt.npy +3 -0
  10. speaker_embeddings/de_speaker_0_fine_prompt.npy +3 -0
  11. speaker_embeddings/de_speaker_0_semantic_prompt.npy +3 -0
  12. speaker_embeddings/de_speaker_1_coarse_prompt.npy +3 -0
  13. speaker_embeddings/de_speaker_1_fine_prompt.npy +3 -0
  14. speaker_embeddings/de_speaker_1_semantic_prompt.npy +3 -0
  15. speaker_embeddings/de_speaker_2_coarse_prompt.npy +3 -0
  16. speaker_embeddings/de_speaker_2_fine_prompt.npy +3 -0
  17. speaker_embeddings/de_speaker_2_semantic_prompt.npy +3 -0
  18. speaker_embeddings/de_speaker_3_coarse_prompt.npy +3 -0
  19. speaker_embeddings/de_speaker_3_fine_prompt.npy +3 -0
  20. speaker_embeddings/de_speaker_3_semantic_prompt.npy +3 -0
  21. speaker_embeddings/de_speaker_4_coarse_prompt.npy +3 -0
  22. speaker_embeddings/de_speaker_4_fine_prompt.npy +3 -0
  23. speaker_embeddings/de_speaker_4_semantic_prompt.npy +3 -0
  24. speaker_embeddings/de_speaker_5_coarse_prompt.npy +3 -0
  25. speaker_embeddings/de_speaker_5_fine_prompt.npy +3 -0
  26. speaker_embeddings/de_speaker_5_semantic_prompt.npy +3 -0
  27. speaker_embeddings/de_speaker_6_coarse_prompt.npy +3 -0
  28. speaker_embeddings/de_speaker_6_fine_prompt.npy +3 -0
  29. speaker_embeddings/de_speaker_6_semantic_prompt.npy +3 -0
  30. speaker_embeddings/de_speaker_7_coarse_prompt.npy +3 -0
  31. speaker_embeddings/de_speaker_7_fine_prompt.npy +3 -0
  32. speaker_embeddings/de_speaker_7_semantic_prompt.npy +3 -0
  33. speaker_embeddings/de_speaker_8_coarse_prompt.npy +3 -0
  34. speaker_embeddings/de_speaker_8_fine_prompt.npy +3 -0
  35. speaker_embeddings/de_speaker_8_semantic_prompt.npy +3 -0
  36. speaker_embeddings/de_speaker_9_coarse_prompt.npy +3 -0
  37. speaker_embeddings/de_speaker_9_fine_prompt.npy +3 -0
  38. speaker_embeddings/de_speaker_9_semantic_prompt.npy +3 -0
  39. speaker_embeddings/en_speaker_0_coarse_prompt.npy +3 -0
  40. speaker_embeddings/en_speaker_0_fine_prompt.npy +3 -0
  41. speaker_embeddings/en_speaker_0_semantic_prompt.npy +3 -0
  42. speaker_embeddings/en_speaker_1_coarse_prompt.npy +3 -0
  43. speaker_embeddings/en_speaker_1_fine_prompt.npy +3 -0
  44. speaker_embeddings/en_speaker_1_semantic_prompt.npy +3 -0
  45. speaker_embeddings/en_speaker_2_coarse_prompt.npy +3 -0
  46. speaker_embeddings/en_speaker_2_fine_prompt.npy +3 -0
  47. speaker_embeddings/en_speaker_2_semantic_prompt.npy +3 -0
  48. speaker_embeddings/en_speaker_3_coarse_prompt.npy +3 -0
  49. speaker_embeddings/en_speaker_3_fine_prompt.npy +3 -0
  50. speaker_embeddings/en_speaker_3_semantic_prompt.npy +3 -0
.gitattributes ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ *.7z filter=lfs diff=lfs merge=lfs -text
2
+ *.arrow filter=lfs diff=lfs merge=lfs -text
3
+ *.bin filter=lfs diff=lfs merge=lfs -text
4
+ *.bz2 filter=lfs diff=lfs merge=lfs -text
5
+ *.ckpt filter=lfs diff=lfs merge=lfs -text
6
+ *.ftz filter=lfs diff=lfs merge=lfs -text
7
+ *.gz filter=lfs diff=lfs merge=lfs -text
8
+ *.h5 filter=lfs diff=lfs merge=lfs -text
9
+ *.joblib filter=lfs diff=lfs merge=lfs -text
10
+ *.lfs.* filter=lfs diff=lfs merge=lfs -text
11
+ *.mlmodel filter=lfs diff=lfs merge=lfs -text
12
+ *.model filter=lfs diff=lfs merge=lfs -text
13
+ *.msgpack filter=lfs diff=lfs merge=lfs -text
14
+ *.npy filter=lfs diff=lfs merge=lfs -text
15
+ *.npz filter=lfs diff=lfs merge=lfs -text
16
+ *.onnx filter=lfs diff=lfs merge=lfs -text
17
+ *.ot filter=lfs diff=lfs merge=lfs -text
18
+ *.parquet filter=lfs diff=lfs merge=lfs -text
19
+ *.pb filter=lfs diff=lfs merge=lfs -text
20
+ *.pickle filter=lfs diff=lfs merge=lfs -text
21
+ *.pkl filter=lfs diff=lfs merge=lfs -text
22
+ *.pt filter=lfs diff=lfs merge=lfs -text
23
+ *.pth filter=lfs diff=lfs merge=lfs -text
24
+ *.rar filter=lfs diff=lfs merge=lfs -text
25
+ *.safetensors filter=lfs diff=lfs merge=lfs -text
26
+ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
27
+ *.tar.* filter=lfs diff=lfs merge=lfs -text
28
+ *.tflite filter=lfs diff=lfs merge=lfs -text
29
+ *.tgz filter=lfs diff=lfs merge=lfs -text
30
+ *.wasm filter=lfs diff=lfs merge=lfs -text
31
+ *.xz filter=lfs diff=lfs merge=lfs -text
32
+ *.zip filter=lfs diff=lfs merge=lfs -text
33
+ *.zst filter=lfs diff=lfs merge=lfs -text
34
+ *tfevents* filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,190 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language:
3
+ - en
4
+ - de
5
+ - es
6
+ - fr
7
+ - hi
8
+ - it
9
+ - ja
10
+ - ko
11
+ - pl
12
+ - pt
13
+ - ru
14
+ - tr
15
+ - zh
16
+ thumbnail: >-
17
+ https://user-images.githubusercontent.com/5068315/230698495-cbb1ced9-c911-4c9a-941d-a1a4a1286ac6.png
18
+ library: bark
19
+ license: cc-by-nc-4.0
20
+ tags:
21
+ - bark
22
+ - audio
23
+ - text-to-speech
24
+ duplicated_from: ylacombe/bark-small
25
+ ---
26
+
27
+ # Bark
28
+
29
+ Bark is a transformer-based text-to-audio model created by [Suno](https://www.suno.ai).
30
+ Bark can generate highly realistic, multilingual speech as well as other audio - including music,
31
+ background noise and simple sound effects. The model can also produce nonverbal
32
+ communications like laughing, sighing and crying. To support the research community,
33
+ we are providing access to pretrained model checkpoints ready for inference.
34
+
35
+ The original github repo and model card can be found [here](https://github.com/suno-ai/bark).
36
+
37
+ This model is meant for research purposes only.
38
+ The model output is not censored and the authors do not endorse the opinions in the generated content.
39
+ Use at your own risk.
40
+
41
+ Two checkpoints are released:
42
+ - [**small** (this checkpoint)](https://huggingface.co/suno/bark-small)
43
+ - [large](https://huggingface.co/suno/bark)
44
+
45
+
46
+ ## Example
47
+
48
+ Try out Bark yourself!
49
+
50
+ * Bark Colab:
51
+
52
+ <a target="_blank" href="https://colab.research.google.com/drive/1eJfA2XUa-mXwdMy7DoYKVYHI1iTd9Vkt?usp=sharing">
53
+ <img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"/>
54
+ </a>
55
+
56
+ * Hugging Face Colab:
57
+
58
+ <a target="_blank" href="https://colab.research.google.com/drive/1dWWkZzvu7L9Bunq9zvD-W02RFUXoW-Pd?usp=sharing">
59
+ <img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"/>
60
+ </a>
61
+
62
+ * Hugging Face Demo:
63
+
64
+ <a target="_blank" href="https://huggingface.co/spaces/suno/bark">
65
+ <img src="https://huggingface.co/datasets/huggingface/badges/raw/main/open-in-hf-spaces-sm.svg" alt="Open in HuggingFace"/>
66
+ </a>
67
+
68
+
69
+ ## 🤗 Transformers Usage
70
+
71
+
72
+ You can run Bark locally with the 🤗 Transformers library from version 4.31.0 onwards.
73
+
74
+ 1. First install the 🤗 [Transformers library](https://github.com/huggingface/transformers) from main:
75
+
76
+ ```
77
+ pip install git+https://github.com/huggingface/transformers.git
78
+ ```
79
+
80
+ 2. Run the following Python code to generate speech samples:
81
+
82
+ ```python
83
+ from transformers import AutoProcessor, AutoModel
84
+
85
+
86
+ processor = AutoProcessor.from_pretrained("suno/bark-small")
87
+ model = AutoModel.from_pretrained("suno/bark-small")
88
+
89
+ inputs = processor(
90
+ text=["Hello, my name is Suno. And, uh — and I like pizza. [laughs] But I also have other interests such as playing tic tac toe."],
91
+ return_tensors="pt",
92
+ )
93
+
94
+ speech_values = model.generate(**inputs, do_sample=True)
95
+ ```
96
+
97
+ 3. Listen to the speech samples either in an ipynb notebook:
98
+
99
+ ```python
100
+ from IPython.display import Audio
101
+
102
+ sampling_rate = model.generation_config.sample_rate
103
+ Audio(speech_values.cpu().numpy().squeeze(), rate=sampling_rate)
104
+ ```
105
+
106
+ Or save them as a `.wav` file using a third-party library, e.g. `scipy`:
107
+
108
+ ```python
109
+ import scipy
110
+
111
+ sampling_rate = model.config.sample_rate
112
+ scipy.io.wavfile.write("bark_out.wav", rate=sampling_rate, data=speech_values.cpu().numpy().squeeze())
113
+ ```
114
+
115
+ For more details on using the Bark model for inference using the 🤗 Transformers library, refer to the [Bark docs](https://huggingface.co/docs/transformers/model_doc/bark).
116
+
117
+ ## Suno Usage
118
+
119
+ You can also run Bark locally through the original [Bark library]((https://github.com/suno-ai/bark):
120
+
121
+ 1. First install the [`bark` library](https://github.com/suno-ai/bark)
122
+
123
+ 3. Run the following Python code:
124
+
125
+ ```python
126
+ from bark import SAMPLE_RATE, generate_audio, preload_models
127
+ from IPython.display import Audio
128
+
129
+ # download and load all models
130
+ preload_models()
131
+
132
+ # generate audio from text
133
+ text_prompt = """
134
+ Hello, my name is Suno. And, uh — and I like pizza. [laughs]
135
+ But I also have other interests such as playing tic tac toe.
136
+ """
137
+ speech_array = generate_audio(text_prompt)
138
+
139
+ # play text in notebook
140
+ Audio(speech_array, rate=SAMPLE_RATE)
141
+ ```
142
+
143
+ [pizza.webm](https://user-images.githubusercontent.com/5068315/230490503-417e688d-5115-4eee-9550-b46a2b465ee3.webm)
144
+
145
+
146
+ To save `audio_array` as a WAV file:
147
+
148
+ ```python
149
+ from scipy.io.wavfile import write as write_wav
150
+
151
+ write_wav("/path/to/audio.wav", SAMPLE_RATE, audio_array)
152
+ ```
153
+
154
+ ## Model Details
155
+
156
+
157
+ The following is additional information about the models released here.
158
+
159
+ Bark is a series of three transformer models that turn text into audio.
160
+
161
+ ### Text to semantic tokens
162
+ - Input: text, tokenized with [BERT tokenizer from Hugging Face](https://huggingface.co/docs/transformers/model_doc/bert#transformers.BertTokenizer)
163
+ - Output: semantic tokens that encode the audio to be generated
164
+
165
+ ### Semantic to coarse tokens
166
+ - Input: semantic tokens
167
+ - Output: tokens from the first two codebooks of the [EnCodec Codec](https://github.com/facebookresearch/encodec) from facebook
168
+
169
+ ### Coarse to fine tokens
170
+ - Input: the first two codebooks from EnCodec
171
+ - Output: 8 codebooks from EnCodec
172
+
173
+ ### Architecture
174
+ | Model | Parameters | Attention | Output Vocab size |
175
+ |:-------------------------:|:----------:|------------|:-----------------:|
176
+ | Text to semantic tokens | 80/300 M | Causal | 10,000 |
177
+ | Semantic to coarse tokens | 80/300 M | Causal | 2x 1,024 |
178
+ | Coarse to fine tokens | 80/300 M | Non-causal | 6x 1,024 |
179
+
180
+
181
+ ### Release date
182
+ April 2023
183
+
184
+ ## Broader Implications
185
+ We anticipate that this model's text to audio capabilities can be used to improve accessbility tools in a variety of languages.
186
+
187
+ While we hope that this release will enable users to express their creativity and build applications that are a force
188
+ for good, we acknowledge that any text to audio model has the potential for dual use. While it is not straightforward
189
+ to voice clone known people with Bark, it can still be used for nefarious purposes. To further reduce the chances of unintended use of Bark,
190
+ we also release a simple classifier to detect Bark-generated audio with high accuracy (see notebooks section of the main repository).
config.json ADDED
@@ -0,0 +1,340 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_commit_hash": null,
3
+ "architectures": [
4
+ "BarkModel"
5
+ ],
6
+ "coarse_acoustics_config": {
7
+ "_name_or_path": "",
8
+ "add_cross_attention": false,
9
+ "architectures": [
10
+ "BarkCoarseModel"
11
+ ],
12
+ "bad_words_ids": null,
13
+ "begin_suppress_tokens": null,
14
+ "bias": false,
15
+ "block_size": 1024,
16
+ "bos_token_id": null,
17
+ "chunk_size_feed_forward": 0,
18
+ "cross_attention_hidden_size": null,
19
+ "decoder_start_token_id": null,
20
+ "diversity_penalty": 0.0,
21
+ "do_sample": false,
22
+ "dropout": 0.0,
23
+ "early_stopping": false,
24
+ "encoder_no_repeat_ngram_size": 0,
25
+ "eos_token_id": null,
26
+ "exponential_decay_length_penalty": null,
27
+ "finetuning_task": null,
28
+ "forced_bos_token_id": null,
29
+ "forced_eos_token_id": null,
30
+ "hidden_size": 768,
31
+ "id2label": {
32
+ "0": "LABEL_0",
33
+ "1": "LABEL_1"
34
+ },
35
+ "initializer_range": 0.02,
36
+ "input_vocab_size": 12096,
37
+ "is_decoder": false,
38
+ "is_encoder_decoder": false,
39
+ "label2id": {
40
+ "LABEL_0": 0,
41
+ "LABEL_1": 1
42
+ },
43
+ "length_penalty": 1.0,
44
+ "max_length": 20,
45
+ "min_length": 0,
46
+ "model_type": "coarse_acoustics",
47
+ "no_repeat_ngram_size": 0,
48
+ "num_beam_groups": 1,
49
+ "num_beams": 1,
50
+ "num_heads": 12,
51
+ "num_layers": 12,
52
+ "num_return_sequences": 1,
53
+ "output_attentions": false,
54
+ "output_hidden_states": false,
55
+ "output_scores": false,
56
+ "output_vocab_size": 12096,
57
+ "pad_token_id": null,
58
+ "prefix": null,
59
+ "problem_type": null,
60
+ "pruned_heads": {},
61
+ "remove_invalid_values": false,
62
+ "repetition_penalty": 1.0,
63
+ "return_dict": true,
64
+ "return_dict_in_generate": false,
65
+ "sep_token_id": null,
66
+ "suppress_tokens": null,
67
+ "task_specific_params": null,
68
+ "temperature": 1.0,
69
+ "tf_legacy_loss": false,
70
+ "tie_encoder_decoder": false,
71
+ "tie_word_embeddings": true,
72
+ "tokenizer_class": null,
73
+ "top_k": 50,
74
+ "top_p": 1.0,
75
+ "torch_dtype": "float32",
76
+ "torchscript": false,
77
+ "transformers_version": "4.31.0.dev0",
78
+ "typical_p": 1.0,
79
+ "use_bfloat16": false,
80
+ "use_cache": true
81
+ },
82
+ "codec_config": {
83
+ "_name_or_path": "ArthurZ/encodec_24khz",
84
+ "add_cross_attention": false,
85
+ "architectures": [
86
+ "EncodecModel"
87
+ ],
88
+ "audio_channels": 1,
89
+ "bad_words_ids": null,
90
+ "begin_suppress_tokens": null,
91
+ "bos_token_id": null,
92
+ "chunk_length_s": null,
93
+ "chunk_size_feed_forward": 0,
94
+ "codebook_dim": 128,
95
+ "codebook_size": 1024,
96
+ "compress": 2,
97
+ "cross_attention_hidden_size": null,
98
+ "decoder_start_token_id": null,
99
+ "dilation_growth_rate": 2,
100
+ "diversity_penalty": 0.0,
101
+ "do_sample": false,
102
+ "early_stopping": false,
103
+ "encoder_no_repeat_ngram_size": 0,
104
+ "eos_token_id": null,
105
+ "exponential_decay_length_penalty": null,
106
+ "finetuning_task": null,
107
+ "forced_bos_token_id": null,
108
+ "forced_eos_token_id": null,
109
+ "hidden_size": 128,
110
+ "id2label": {
111
+ "0": "LABEL_0",
112
+ "1": "LABEL_1"
113
+ },
114
+ "is_decoder": false,
115
+ "is_encoder_decoder": false,
116
+ "kernel_size": 7,
117
+ "label2id": {
118
+ "LABEL_0": 0,
119
+ "LABEL_1": 1
120
+ },
121
+ "last_kernel_size": 7,
122
+ "length_penalty": 1.0,
123
+ "max_length": 20,
124
+ "min_length": 0,
125
+ "model_type": "encodec",
126
+ "no_repeat_ngram_size": 0,
127
+ "norm_type": "weight_norm",
128
+ "normalize": false,
129
+ "num_beam_groups": 1,
130
+ "num_beams": 1,
131
+ "num_filters": 32,
132
+ "num_lstm_layers": 2,
133
+ "num_residual_layers": 1,
134
+ "num_return_sequences": 1,
135
+ "output_attentions": false,
136
+ "output_hidden_states": false,
137
+ "output_scores": false,
138
+ "overlap": null,
139
+ "pad_mode": "reflect",
140
+ "pad_token_id": null,
141
+ "prefix": null,
142
+ "problem_type": null,
143
+ "pruned_heads": {},
144
+ "remove_invalid_values": false,
145
+ "repetition_penalty": 1.0,
146
+ "residual_kernel_size": 3,
147
+ "return_dict": true,
148
+ "return_dict_in_generate": false,
149
+ "sampling_rate": 24000,
150
+ "sep_token_id": null,
151
+ "suppress_tokens": null,
152
+ "target_bandwidths": [
153
+ 1.5,
154
+ 3.0,
155
+ 6.0,
156
+ 12.0,
157
+ 24.0
158
+ ],
159
+ "task_specific_params": null,
160
+ "temperature": 1.0,
161
+ "tf_legacy_loss": false,
162
+ "tie_encoder_decoder": false,
163
+ "tie_word_embeddings": true,
164
+ "tokenizer_class": null,
165
+ "top_k": 50,
166
+ "top_p": 1.0,
167
+ "torch_dtype": "float32",
168
+ "torchscript": false,
169
+ "transformers_version": "4.31.0.dev0",
170
+ "trim_right_ratio": 1.0,
171
+ "typical_p": 1.0,
172
+ "upsampling_ratios": [
173
+ 8,
174
+ 5,
175
+ 4,
176
+ 2
177
+ ],
178
+ "use_bfloat16": false,
179
+ "use_causal_conv": true,
180
+ "use_conv_shortcut": true
181
+ },
182
+ "fine_acoustics_config": {
183
+ "_name_or_path": "",
184
+ "add_cross_attention": false,
185
+ "architectures": [
186
+ "BarkFineModel"
187
+ ],
188
+ "bad_words_ids": null,
189
+ "begin_suppress_tokens": null,
190
+ "bias": false,
191
+ "block_size": 1024,
192
+ "bos_token_id": null,
193
+ "chunk_size_feed_forward": 0,
194
+ "cross_attention_hidden_size": null,
195
+ "decoder_start_token_id": null,
196
+ "diversity_penalty": 0.0,
197
+ "do_sample": false,
198
+ "dropout": 0.0,
199
+ "early_stopping": false,
200
+ "encoder_no_repeat_ngram_size": 0,
201
+ "eos_token_id": null,
202
+ "exponential_decay_length_penalty": null,
203
+ "finetuning_task": null,
204
+ "forced_bos_token_id": null,
205
+ "forced_eos_token_id": null,
206
+ "hidden_size": 768,
207
+ "id2label": {
208
+ "0": "LABEL_0",
209
+ "1": "LABEL_1"
210
+ },
211
+ "initializer_range": 0.02,
212
+ "input_vocab_size": 1056,
213
+ "is_decoder": false,
214
+ "is_encoder_decoder": false,
215
+ "label2id": {
216
+ "LABEL_0": 0,
217
+ "LABEL_1": 1
218
+ },
219
+ "length_penalty": 1.0,
220
+ "max_length": 20,
221
+ "min_length": 0,
222
+ "model_type": "fine_acoustics",
223
+ "n_codes_given": 1,
224
+ "n_codes_total": 8,
225
+ "no_repeat_ngram_size": 0,
226
+ "num_beam_groups": 1,
227
+ "num_beams": 1,
228
+ "num_heads": 12,
229
+ "num_layers": 12,
230
+ "num_return_sequences": 1,
231
+ "output_attentions": false,
232
+ "output_hidden_states": false,
233
+ "output_scores": false,
234
+ "output_vocab_size": 1056,
235
+ "pad_token_id": null,
236
+ "prefix": null,
237
+ "problem_type": null,
238
+ "pruned_heads": {},
239
+ "remove_invalid_values": false,
240
+ "repetition_penalty": 1.0,
241
+ "return_dict": true,
242
+ "return_dict_in_generate": false,
243
+ "sep_token_id": null,
244
+ "suppress_tokens": null,
245
+ "task_specific_params": null,
246
+ "temperature": 1.0,
247
+ "tf_legacy_loss": false,
248
+ "tie_encoder_decoder": false,
249
+ "tie_word_embeddings": true,
250
+ "tokenizer_class": null,
251
+ "top_k": 50,
252
+ "top_p": 1.0,
253
+ "torch_dtype": "float32",
254
+ "torchscript": false,
255
+ "transformers_version": "4.31.0.dev0",
256
+ "typical_p": 1.0,
257
+ "use_bfloat16": false,
258
+ "use_cache": true
259
+ },
260
+ "initializer_range": 0.02,
261
+ "model_type": "bark",
262
+ "semantic_config": {
263
+ "_name_or_path": "",
264
+ "add_cross_attention": false,
265
+ "architectures": [
266
+ "BarkSemanticModel"
267
+ ],
268
+ "bad_words_ids": null,
269
+ "begin_suppress_tokens": null,
270
+ "bias": false,
271
+ "block_size": 1024,
272
+ "bos_token_id": null,
273
+ "chunk_size_feed_forward": 0,
274
+ "cross_attention_hidden_size": null,
275
+ "decoder_start_token_id": null,
276
+ "diversity_penalty": 0.0,
277
+ "do_sample": false,
278
+ "dropout": 0.0,
279
+ "early_stopping": false,
280
+ "encoder_no_repeat_ngram_size": 0,
281
+ "eos_token_id": null,
282
+ "exponential_decay_length_penalty": null,
283
+ "finetuning_task": null,
284
+ "forced_bos_token_id": null,
285
+ "forced_eos_token_id": null,
286
+ "hidden_size": 768,
287
+ "id2label": {
288
+ "0": "LABEL_0",
289
+ "1": "LABEL_1"
290
+ },
291
+ "initializer_range": 0.02,
292
+ "input_vocab_size": 129600,
293
+ "is_decoder": false,
294
+ "is_encoder_decoder": false,
295
+ "label2id": {
296
+ "LABEL_0": 0,
297
+ "LABEL_1": 1
298
+ },
299
+ "length_penalty": 1.0,
300
+ "max_length": 20,
301
+ "min_length": 0,
302
+ "model_type": "semantic",
303
+ "no_repeat_ngram_size": 0,
304
+ "num_beam_groups": 1,
305
+ "num_beams": 1,
306
+ "num_heads": 12,
307
+ "num_layers": 12,
308
+ "num_return_sequences": 1,
309
+ "output_attentions": false,
310
+ "output_hidden_states": false,
311
+ "output_scores": false,
312
+ "output_vocab_size": 10048,
313
+ "pad_token_id": null,
314
+ "prefix": null,
315
+ "problem_type": null,
316
+ "pruned_heads": {},
317
+ "remove_invalid_values": false,
318
+ "repetition_penalty": 1.0,
319
+ "return_dict": true,
320
+ "return_dict_in_generate": false,
321
+ "sep_token_id": null,
322
+ "suppress_tokens": null,
323
+ "task_specific_params": null,
324
+ "temperature": 1.0,
325
+ "tf_legacy_loss": false,
326
+ "tie_encoder_decoder": false,
327
+ "tie_word_embeddings": true,
328
+ "tokenizer_class": null,
329
+ "top_k": 50,
330
+ "top_p": 1.0,
331
+ "torch_dtype": "float32",
332
+ "torchscript": false,
333
+ "transformers_version": "4.31.0.dev0",
334
+ "typical_p": 1.0,
335
+ "use_bfloat16": false,
336
+ "use_cache": true
337
+ },
338
+ "torch_dtype": "float32",
339
+ "transformers_version": null
340
+ }
generation_config.json ADDED
@@ -0,0 +1,172 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "guidance_scale": null,
27
+ "length_penalty": 1.0,
28
+ "max_coarse_history": 630,
29
+ "max_coarse_input_length": 256,
30
+ "max_length": 20,
31
+ "max_new_tokens": null,
32
+ "max_time": null,
33
+ "min_length": 0,
34
+ "min_new_tokens": null,
35
+ "n_coarse_codebooks": 2,
36
+ "no_repeat_ngram_size": 0,
37
+ "num_beam_groups": 1,
38
+ "num_beams": 1,
39
+ "num_return_sequences": 1,
40
+ "output_attentions": false,
41
+ "output_hidden_states": false,
42
+ "output_scores": false,
43
+ "pad_token_id": null,
44
+ "penalty_alpha": null,
45
+ "remove_invalid_values": false,
46
+ "renormalize_logits": true,
47
+ "repetition_penalty": 1.0,
48
+ "return_dict_in_generate": false,
49
+ "sequence_bias": null,
50
+ "sliding_window_len": 60,
51
+ "suppress_tokens": null,
52
+ "temperature": 0.7,
53
+ "top_k": 50,
54
+ "top_p": 1.0,
55
+ "transformers_version": "4.31.0.dev0",
56
+ "typical_p": 1.0,
57
+ "use_cache": true
58
+ },
59
+ "codebook_size": 1024,
60
+ "fine_acoustics_config": {
61
+ "_from_model_config": false,
62
+ "bad_words_ids": null,
63
+ "begin_suppress_tokens": null,
64
+ "bos_token_id": null,
65
+ "constraints": null,
66
+ "decoder_start_token_id": null,
67
+ "diversity_penalty": 0.0,
68
+ "do_sample": false,
69
+ "early_stopping": false,
70
+ "encoder_no_repeat_ngram_size": 0,
71
+ "encoder_repetition_penalty": 1.0,
72
+ "eos_token_id": null,
73
+ "epsilon_cutoff": 0.0,
74
+ "eta_cutoff": 0.0,
75
+ "exponential_decay_length_penalty": null,
76
+ "force_words_ids": null,
77
+ "forced_bos_token_id": null,
78
+ "forced_decoder_ids": null,
79
+ "forced_eos_token_id": null,
80
+ "generation_kwargs": {},
81
+ "guidance_scale": null,
82
+ "length_penalty": 1.0,
83
+ "max_fine_history_length": 512,
84
+ "max_fine_input_length": 1024,
85
+ "max_length": 20,
86
+ "max_new_tokens": null,
87
+ "max_time": null,
88
+ "min_length": 0,
89
+ "min_new_tokens": null,
90
+ "n_fine_codebooks": 8,
91
+ "no_repeat_ngram_size": 0,
92
+ "num_beam_groups": 1,
93
+ "num_beams": 1,
94
+ "num_return_sequences": 1,
95
+ "output_attentions": false,
96
+ "output_hidden_states": false,
97
+ "output_scores": false,
98
+ "pad_token_id": null,
99
+ "penalty_alpha": null,
100
+ "remove_invalid_values": false,
101
+ "renormalize_logits": false,
102
+ "repetition_penalty": 1.0,
103
+ "return_dict_in_generate": false,
104
+ "sequence_bias": null,
105
+ "suppress_tokens": null,
106
+ "temperature": 0.5,
107
+ "top_k": 50,
108
+ "top_p": 1.0,
109
+ "transformers_version": "4.31.0.dev0",
110
+ "typical_p": 1.0,
111
+ "use_cache": true
112
+ },
113
+ "model_type": "bark",
114
+ "sample_rate": 24000,
115
+ "semantic_config": {
116
+ "_from_model_config": false,
117
+ "bad_words_ids": null,
118
+ "begin_suppress_tokens": null,
119
+ "bos_token_id": null,
120
+ "constraints": null,
121
+ "decoder_start_token_id": null,
122
+ "diversity_penalty": 0.0,
123
+ "do_sample": true,
124
+ "early_stopping": false,
125
+ "encoder_no_repeat_ngram_size": 0,
126
+ "encoder_repetition_penalty": 1.0,
127
+ "eos_token_id": 10000,
128
+ "epsilon_cutoff": 0.0,
129
+ "eta_cutoff": 0.0,
130
+ "exponential_decay_length_penalty": null,
131
+ "force_words_ids": null,
132
+ "forced_bos_token_id": null,
133
+ "forced_decoder_ids": null,
134
+ "forced_eos_token_id": null,
135
+ "generation_kwargs": {},
136
+ "guidance_scale": null,
137
+ "length_penalty": 1.0,
138
+ "max_input_semantic_length": 256,
139
+ "max_length": 20,
140
+ "max_new_tokens": 768,
141
+ "max_time": null,
142
+ "min_length": 0,
143
+ "min_new_tokens": null,
144
+ "no_repeat_ngram_size": 0,
145
+ "num_beam_groups": 1,
146
+ "num_beams": 1,
147
+ "num_return_sequences": 1,
148
+ "output_attentions": false,
149
+ "output_hidden_states": false,
150
+ "output_scores": false,
151
+ "pad_token_id": null,
152
+ "penalty_alpha": null,
153
+ "remove_invalid_values": false,
154
+ "renormalize_logits": true,
155
+ "repetition_penalty": 1.0,
156
+ "return_dict_in_generate": false,
157
+ "semantic_infer_token": 129599,
158
+ "semantic_pad_token": 10000,
159
+ "semantic_rate_hz": 49.9,
160
+ "semantic_vocab_size": 10000,
161
+ "sequence_bias": null,
162
+ "suppress_tokens": null,
163
+ "temperature": 0.7,
164
+ "text_encoding_offset": 10048,
165
+ "text_pad_token": 129595,
166
+ "top_k": 50,
167
+ "top_p": 1.0,
168
+ "transformers_version": "4.31.0.dev0",
169
+ "typical_p": 1.0,
170
+ "use_cache": true
171
+ }
172
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f0f7f16b24f65789ce42b3c491aa6a1cdf219f7ef425066fcd194485245e65d9
3
+ size 1676663913
speaker_embeddings/announcer_coarse_prompt.npy ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2c77d5e1f9ab39e489d27628ab26dfae7a8b4cae4ba72658a1a94927f7ff5132
3
+ size 3128
speaker_embeddings/announcer_fine_prompt.npy ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7aac73cd2a14c1939a718aeb48b064d149b39f773f1dcc9b93be6f79ebd33755
3
+ size 12128
speaker_embeddings/announcer_semantic_prompt.npy ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f5564642cbd84db6f4d1d8a522bd26329b4f4cd8cd81e1965b90baf1ee80c7ff
3
+ size 1126
speaker_embeddings/de_speaker_0_coarse_prompt.npy ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3eb78af32779b5fabbb92e7cdbdeaaa34f5f8ad1085e213b101165665c5ce4cb
3
+ size 9472
speaker_embeddings/de_speaker_0_fine_prompt.npy ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a2421bcbeb7fadfcf1c0b33e38e316474d4a95139d4dd0b3d861e72c8fd77c36
3
+ size 18816
speaker_embeddings/de_speaker_0_semantic_prompt.npy ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:44e5539dbcd158a2471c59b46cde7f0564d108cd2fd935e3664b2ec733ad4393
3
+ size 3240
speaker_embeddings/de_speaker_1_coarse_prompt.npy ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6ac93157e39cd0fa7a5e9d0404d6adcb3daaec8e820b42b72b96de62e19ca89b
3
+ size 9472
speaker_embeddings/de_speaker_1_fine_prompt.npy ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9f8eaca4b732dd3264213ac387f4c91f83a574563b0d72368b237df03fe92b4d
3
+ size 18816
speaker_embeddings/de_speaker_1_semantic_prompt.npy ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:98cde60e36a6265d6534e4c6422436f201a9bfcdc87f9817d6faf6ab4f22554b
3
+ size 3240
speaker_embeddings/de_speaker_2_coarse_prompt.npy ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fd5e9d07b0480dda2c3661de1da0671f34419c029c8e7410705139a38fb133d3
3
+ size 6944
speaker_embeddings/de_speaker_2_fine_prompt.npy ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4f11b22a8a24428ca0114e4fcc770c0ca554376de95be7ac5ac560ae4f1988fb
3
+ size 13760
speaker_embeddings/de_speaker_2_semantic_prompt.npy ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8efe5707a724632900ab5cb274ffdbac0d39fd6dda1be49833d63311df478ef3
3
+ size 2400
speaker_embeddings/de_speaker_3_coarse_prompt.npy ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf0fb48dd18c79996fc800abbd3407dd967b21a36bda695584e29d302ead274a
3
+ size 8608
speaker_embeddings/de_speaker_3_fine_prompt.npy ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:229455388c628e9d168ad11940041b15ed3b40f724ab3a4747f6cb38b2f5230a
3
+ size 17088
speaker_embeddings/de_speaker_3_semantic_prompt.npy ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:88fee5c6b974dbfb1168b55f73990be270847a91a2e7895d298b188f3ad7da9f
3
+ size 2952
speaker_embeddings/de_speaker_4_coarse_prompt.npy ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0268e63ef8aa7c6113af4a840c3581c08edea0eacec8aaa7d52da8012d8c16f5
3
+ size 5984
speaker_embeddings/de_speaker_4_fine_prompt.npy ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:21c41cce8756afcd8b690ad8701e35f33b4c0be3c63bae5f6ebbc10e5cb3c150
3
+ size 11840
speaker_embeddings/de_speaker_4_semantic_prompt.npy ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a03e84c7f1f4dd97f033d999fea8eb76c4dde6883e1dae67303b6a46bdb57803
3
+ size 2080
speaker_embeddings/de_speaker_5_coarse_prompt.npy ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3f4272d4c3928264a36a406b9c0d306db99316180dca8e96504c93244fc61d96
3
+ size 10416
speaker_embeddings/de_speaker_5_fine_prompt.npy ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dac52541ccb321598997fe0e27ebadf5540eb6e53a8b3a614d7cabfcbae4b2d0
3
+ size 20704
speaker_embeddings/de_speaker_5_semantic_prompt.npy ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:412b3a1f45525390e84bd2109bb86af782da2245adcbdd8803c1b362a311075c
3
+ size 3552
speaker_embeddings/de_speaker_6_coarse_prompt.npy ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bc029718234023df88f9ae4ea830a90115bd2256b10fe8c3c725483392c0f6c2
3
+ size 9408
speaker_embeddings/de_speaker_6_fine_prompt.npy ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3414b015ad3567a2590f5b044f3d2043270bef8b03cb1348b7265d21bbca2299
3
+ size 18688
speaker_embeddings/de_speaker_6_semantic_prompt.npy ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2300ace5fda24f16a27b345a6f54c19e2e2363808cac0a58bac12518b4c8f77d
3
+ size 3216
speaker_embeddings/de_speaker_7_coarse_prompt.npy ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd86cb193cb39a077a2cb2540af2953ce7f2f480ec3129c5191e730b87329493
3
+ size 17696
speaker_embeddings/de_speaker_7_fine_prompt.npy ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6e97d71d8a7120bff91f08ccf1d0e6d1e8b6983642d56dad0cbe0f8dc2554343
3
+ size 35264
speaker_embeddings/de_speaker_7_semantic_prompt.npy ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7be7d81cb55364f3db979ce92315e2e64517203b9300caca6414970ec81c220b
3
+ size 5976
speaker_embeddings/de_speaker_8_coarse_prompt.npy ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:06efd00181d007e30b7b7bede472ea50e9f7c61aa7b76074884d26eec8d965f7
3
+ size 7424
speaker_embeddings/de_speaker_8_fine_prompt.npy ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f566f926840a3e70e115fc41b0bf4c3f658b1b23e8583e7492d7f0ae13423ac5
3
+ size 14720
speaker_embeddings/de_speaker_8_semantic_prompt.npy ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1919388fdd9b0e236e7bdeef4f6ad1416c7b0e49daf72cf5e064b2e2106584aa
3
+ size 2560
speaker_embeddings/de_speaker_9_coarse_prompt.npy ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:97012e37b1d51da9b2aebfb521b568713042cb4e086367dc5f2558c0b6629486
3
+ size 6544
speaker_embeddings/de_speaker_9_fine_prompt.npy ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f455a59e0d759103c7d8802bccef33cf0cafbf9122605179278d6f7ff302acdf
3
+ size 12960
speaker_embeddings/de_speaker_9_semantic_prompt.npy ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8efede4bec02ec98fc470dc53ca00154fea57f895a931ef6f44b1e9621b18ad2
3
+ size 2264
speaker_embeddings/en_speaker_0_coarse_prompt.npy ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1d91b5e26a8c703a7764b21570d8cc94aee3bb043a407c3ace89976f701ddf8f
3
+ size 6608
speaker_embeddings/en_speaker_0_fine_prompt.npy ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:24bebee667439786f17048d4ec3f36460d6d9f9f59495b3076a116e6e3f71f6e
3
+ size 13088
speaker_embeddings/en_speaker_0_semantic_prompt.npy ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:01f0c8e96aee83c19514700491be4326c5a1194631cdd486e1d4b76e4d0c0de0
3
+ size 2288
speaker_embeddings/en_speaker_1_coarse_prompt.npy ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ad174875bc5a8076a568bd61a293a8ab80056b97636e159d0ea7046a10833653
3
+ size 5408
speaker_embeddings/en_speaker_1_fine_prompt.npy ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2f168630b806f09a27cff70e404ecc6aa1a62d30b2478e64c352461bb13e97a6
3
+ size 10688
speaker_embeddings/en_speaker_1_semantic_prompt.npy ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:04fd39ae31c48ce4c2578d25e07f436b671fa900fd526de06d68054735fe4fc6
3
+ size 1888
speaker_embeddings/en_speaker_2_coarse_prompt.npy ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:04018345b2fe98c5a5d86dad0931f8ddad010307c3d3fd3eecc7c89a168747eb
3
+ size 10048
speaker_embeddings/en_speaker_2_fine_prompt.npy ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d860a933d31cda9c8b2220384545b2e7c9e022e8456769326dcb5cfe34f3b5b6
3
+ size 19968
speaker_embeddings/en_speaker_2_semantic_prompt.npy ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:218470a0699f110d856a7b8a75faee823d2d496ebd526dcc81acb65e43176c80
3
+ size 3432
speaker_embeddings/en_speaker_3_coarse_prompt.npy ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ced32dac3a50fd964373f0f3480a3eadb4c8e59e56139e8bf3eb9ddffc1d4e85
3
+ size 11328
speaker_embeddings/en_speaker_3_fine_prompt.npy ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4484bba64f038536de4730f0ff8448f53f5ec4d08e800c239b10b95b6d92cf9c
3
+ size 22528
speaker_embeddings/en_speaker_3_semantic_prompt.npy ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d5b1c9aea37f1bcad457f652437255679936acb0e85719f300d176d5b5e01486
3
+ size 3856