Hugging Face's logo

ylacombe
/
bark-small

Text-to-Speech
Transformers
PyTorch
bark
text-to-audio
audio
Inference Endpoints
Model card Files Community
14

Update embeddings

#10
by ylacombe - opened
base: refs/heads/main
←
from: refs/pr/10
Discussion Files changed
+854
-2547
This view is limited to 50 files because it contains too many changes.  See the raw diff here.
Files changed (50) hide show
  1. README.md +0 -188
  2. config.json +6 -2
  3. generation_config.json +2 -7
  4. pytorch_model.bin +2 -2
  5. speaker_embeddings.npz +3 -0
  6. speaker_embeddings/{de_speaker_0_coarse_prompt.npy → announcer.npz} +2 -2
  7. speaker_embeddings/{announcer_coarse_prompt.npy → de_speaker_0.npz} +2 -2
  8. speaker_embeddings/de_speaker_0_fine_prompt.npy +0 -3
  9. speaker_embeddings/de_speaker_0_semantic_prompt.npy +0 -3
  10. speaker_embeddings/{announcer_fine_prompt.npy → de_speaker_1.npz} +2 -2
  11. speaker_embeddings/de_speaker_1_coarse_prompt.npy +0 -3
  12. speaker_embeddings/de_speaker_1_fine_prompt.npy +0 -3
  13. speaker_embeddings/de_speaker_1_semantic_prompt.npy +0 -3
  14. speaker_embeddings/{announcer_semantic_prompt.npy → de_speaker_2.npz} +2 -2
  15. speaker_embeddings/de_speaker_2_coarse_prompt.npy +0 -3
  16. speaker_embeddings/de_speaker_2_fine_prompt.npy +0 -3
  17. speaker_embeddings/de_speaker_2_semantic_prompt.npy +0 -3
  18. speaker_embeddings/de_speaker_3.npz +3 -0
  19. speaker_embeddings/de_speaker_3_coarse_prompt.npy +0 -3
  20. speaker_embeddings/de_speaker_3_fine_prompt.npy +0 -3
  21. speaker_embeddings/de_speaker_3_semantic_prompt.npy +0 -3
  22. speaker_embeddings/de_speaker_4.npz +3 -0
  23. speaker_embeddings/de_speaker_4_coarse_prompt.npy +0 -3
  24. speaker_embeddings/de_speaker_4_fine_prompt.npy +0 -3
  25. speaker_embeddings/de_speaker_4_semantic_prompt.npy +0 -3
  26. speaker_embeddings/de_speaker_5.npz +3 -0
  27. speaker_embeddings/de_speaker_5_coarse_prompt.npy +0 -3
  28. speaker_embeddings/de_speaker_5_fine_prompt.npy +0 -3
  29. speaker_embeddings/de_speaker_5_semantic_prompt.npy +0 -3
  30. speaker_embeddings/de_speaker_6.npz +3 -0
  31. speaker_embeddings/de_speaker_6_coarse_prompt.npy +0 -3
  32. speaker_embeddings/de_speaker_6_fine_prompt.npy +0 -3
  33. speaker_embeddings/de_speaker_6_semantic_prompt.npy +0 -3
  34. speaker_embeddings/{v2/es_speaker_4_semantic_prompt.npy → de_speaker_7.npz} +2 -2
  35. speaker_embeddings/de_speaker_7_coarse_prompt.npy +0 -3
  36. speaker_embeddings/de_speaker_7_fine_prompt.npy +0 -3
  37. speaker_embeddings/de_speaker_7_semantic_prompt.npy +0 -3
  38. speaker_embeddings/de_speaker_8.npz +3 -0
  39. speaker_embeddings/de_speaker_8_coarse_prompt.npy +0 -3
  40. speaker_embeddings/de_speaker_8_fine_prompt.npy +0 -3
  41. speaker_embeddings/de_speaker_8_semantic_prompt.npy +0 -3
  42. speaker_embeddings/de_speaker_9.npz +3 -0
  43. speaker_embeddings/de_speaker_9_coarse_prompt.npy +0 -3
  44. speaker_embeddings/de_speaker_9_fine_prompt.npy +0 -3
  45. speaker_embeddings/de_speaker_9_semantic_prompt.npy +0 -3
  46. speaker_embeddings/en_speaker_0.npz +3 -0
  47. speaker_embeddings/en_speaker_0_coarse_prompt.npy +0 -3
  48. speaker_embeddings/en_speaker_0_fine_prompt.npy +0 -3
  49. speaker_embeddings/en_speaker_0_semantic_prompt.npy +0 -3
  50. speaker_embeddings/en_speaker_1.npz +3 -0
README.md DELETED
@@ -1,188 +0,0 @@
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: https://user-images.githubusercontent.com/5068315/230698495-cbb1ced9-c911-4c9a-941d-a1a4a1286ac6.png
17
- library: "bark"
18
- license: "cc-by-nc-4.0"
19
- tags:
20
- - bark
21
- - audio
22
- - text-to-speech
23
- ---
24
-
25
- # Bark
26
-
27
- Bark is a transformer-based text-to-audio model created by [Suno](https://www.suno.ai).
28
- Bark can generate highly realistic, multilingual speech as well as other audio - including music,
29
- background noise and simple sound effects. The model can also produce nonverbal
30
- communications like laughing, sighing and crying. To support the research community,
31
- we are providing access to pretrained model checkpoints ready for inference.
32
-
33
- The original github repo and model card can be found [here](https://github.com/suno-ai/bark).
34
-
35
- This model is meant for research purposes only.
36
- The model output is not censored and the authors do not endorse the opinions in the generated content.
37
- Use at your own risk.
38
-
39
- Two checkpoints are released:
40
- - [**small** (this checkpoint)](https://huggingface.co/suno/bark-small)
41
- - [large](https://huggingface.co/suno/bark)
42
-
43
-
44
- ## Example
45
-
46
- Try out Bark yourself!
47
-
48
- * Bark Colab:
49
-
50
- <a target="_blank" href="https://colab.research.google.com/drive/1eJfA2XUa-mXwdMy7DoYKVYHI1iTd9Vkt?usp=sharing">
51
- <img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"/>
52
- </a>
53
-
54
- * Hugging Face Colab:
55
-
56
- <a target="_blank" href="https://colab.research.google.com/drive/1dWWkZzvu7L9Bunq9zvD-W02RFUXoW-Pd?usp=sharing">
57
- <img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"/>
58
- </a>
59
-
60
- * Hugging Face Demo:
61
-
62
- <a target="_blank" href="https://huggingface.co/spaces/suno/bark">
63
- <img src="https://huggingface.co/datasets/huggingface/badges/raw/main/open-in-hf-spaces-sm.svg" alt="Open in HuggingFace"/>
64
- </a>
65
-
66
-
67
- ## 🤗 Transformers Usage
68
-
69
-
70
- You can run Bark locally with the 🤗 Transformers library from version 4.31.0 onwards.
71
-
72
- 1. First install the 🤗 [Transformers library](https://github.com/huggingface/transformers) from main:
73
-
74
- ```
75
- pip install git+https://github.com/huggingface/transformers.git
76
- ```
77
-
78
- 2. Run the following Python code to generate speech samples:
79
-
80
- ```python
81
- from transformers import AutoProcessor, AutoModel
82
-
83
-
84
- processor = AutoProcessor.from_pretrained("suno/bark-small")
85
- model = AutoModel.from_pretrained("suno/bark-small")
86
-
87
- inputs = processor(
88
- 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."],
89
- return_tensors="pt",
90
- )
91
-
92
- speech_values = model.generate(**inputs, do_sample=True)
93
- ```
94
-
95
- 3. Listen to the speech samples either in an ipynb notebook:
96
-
97
- ```python
98
- from IPython.display import Audio
99
-
100
- sampling_rate = model.generation_config.sample_rate
101
- Audio(speech_values.cpu().numpy().squeeze(), rate=sampling_rate)
102
- ```
103
-
104
- Or save them as a `.wav` file using a third-party library, e.g. `scipy`:
105
-
106
- ```python
107
- import scipy
108
-
109
- sampling_rate = model.config.sample_rate
110
- scipy.io.wavfile.write("bark_out.wav", rate=sampling_rate, data=speech_values.cpu().numpy().squeeze())
111
- ```
112
-
113
- 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).
114
-
115
- ## Suno Usage
116
-
117
- You can also run Bark locally through the original [Bark library]((https://github.com/suno-ai/bark):
118
-
119
- 1. First install the [`bark` library](https://github.com/suno-ai/bark)
120
-
121
- 3. Run the following Python code:
122
-
123
- ```python
124
- from bark import SAMPLE_RATE, generate_audio, preload_models
125
- from IPython.display import Audio
126
-
127
- # download and load all models
128
- preload_models()
129
-
130
- # generate audio from text
131
- text_prompt = """
132
- Hello, my name is Suno. And, uh — and I like pizza. [laughs]
133
- But I also have other interests such as playing tic tac toe.
134
- """
135
- speech_array = generate_audio(text_prompt)
136
-
137
- # play text in notebook
138
- Audio(speech_array, rate=SAMPLE_RATE)
139
- ```
140
-
141
- [pizza.webm](https://user-images.githubusercontent.com/5068315/230490503-417e688d-5115-4eee-9550-b46a2b465ee3.webm)
142
-
143
-
144
- To save `audio_array` as a WAV file:
145
-
146
- ```python
147
- from scipy.io.wavfile import write as write_wav
148
-
149
- write_wav("/path/to/audio.wav", SAMPLE_RATE, audio_array)
150
- ```
151
-
152
- ## Model Details
153
-
154
-
155
- The following is additional information about the models released here.
156
-
157
- Bark is a series of three transformer models that turn text into audio.
158
-
159
- ### Text to semantic tokens
160
- - Input: text, tokenized with [BERT tokenizer from Hugging Face](https://huggingface.co/docs/transformers/model_doc/bert#transformers.BertTokenizer)
161
- - Output: semantic tokens that encode the audio to be generated
162
-
163
- ### Semantic to coarse tokens
164
- - Input: semantic tokens
165
- - Output: tokens from the first two codebooks of the [EnCodec Codec](https://github.com/facebookresearch/encodec) from facebook
166
-
167
- ### Coarse to fine tokens
168
- - Input: the first two codebooks from EnCodec
169
- - Output: 8 codebooks from EnCodec
170
-
171
- ### Architecture
172
- | Model | Parameters | Attention | Output Vocab size |
173
- |:-------------------------:|:----------:|------------|:-----------------:|
174
- | Text to semantic tokens | 80/300 M | Causal | 10,000 |
175
- | Semantic to coarse tokens | 80/300 M | Causal | 2x 1,024 |
176
- | Coarse to fine tokens | 80/300 M | Non-causal | 6x 1,024 |
177
-
178
-
179
- ### Release date
180
- April 2023
181
-
182
- ## Broader Implications
183
- We anticipate that this model's text to audio capabilities can be used to improve accessbility tools in a variety of languages.
184
-
185
- While we hope that this release will enable users to express their creativity and build applications that are a force
186
- for good, we acknowledge that any text to audio model has the potential for dual use. While it is not straightforward
187
- 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,
188
- we also release a simple classifier to detect Bark-generated audio with high accuracy (see notebooks section of the main repository).
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
config.json CHANGED
@@ -1,5 +1,6 @@
1
  {
2
  "_commit_hash": null,
 
3
  "architectures": [
4
  "BarkModel"
5
  ],
@@ -44,6 +45,8 @@
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,
@@ -176,8 +179,7 @@
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": "",
@@ -300,6 +302,8 @@
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,
 
1
  {
2
  "_commit_hash": null,
3
+ "_name_or_path": "/home/yoach/bark_weigths/model_small/",
4
  "architectures": [
5
  "BarkModel"
6
  ],
 
45
  "max_length": 20,
46
  "min_length": 0,
47
  "model_type": "coarse_acoustics",
48
+ "n_codes_given": 1,
49
+ "n_codes_total": 8,
50
  "no_repeat_ngram_size": 0,
51
  "num_beam_groups": 1,
52
  "num_beams": 1,
 
179
  2
180
  ],
181
  "use_bfloat16": false,
182
+ "use_causal_conv": true
 
183
  },
184
  "fine_acoustics_config": {
185
  "_name_or_path": "",
 
302
  "max_length": 20,
303
  "min_length": 0,
304
  "model_type": "semantic",
305
+ "n_codes_given": 1,
306
+ "n_codes_total": 8,
307
  "no_repeat_ngram_size": 0,
308
  "num_beam_groups": 1,
309
  "num_beams": 1,
generation_config.json CHANGED
@@ -23,7 +23,6 @@
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,
@@ -46,7 +45,6 @@
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,
@@ -78,7 +76,6 @@
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,
@@ -101,7 +98,6 @@
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,
@@ -133,7 +129,6 @@
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,
@@ -158,7 +153,6 @@
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,
@@ -168,5 +162,6 @@
168
  "transformers_version": "4.31.0.dev0",
169
  "typical_p": 1.0,
170
  "use_cache": true
171
- }
 
172
  }
 
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,
 
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,
 
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,
 
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,
 
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,
 
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,
 
162
  "transformers_version": "4.31.0.dev0",
163
  "typical_p": 1.0,
164
  "use_cache": true
165
+ },
166
+ "transformers_version": "4.31.0.dev0"
167
  }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f0f7f16b24f65789ce42b3c491aa6a1cdf219f7ef425066fcd194485245e65d9
3
- size 1676663913
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dc221dd06f22eb8c6babc17f3d2aaae90dbe4223c7dda46b0a62e2c820bbdabd
3
+ size 1699372613
speaker_embeddings.npz ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e1a05c1153de63f9cd648ba439161923b38b0bc39368e4a3deaf15a2ca446d19
3
+ size 7884740
speaker_embeddings/{de_speaker_0_coarse_prompt.npy → announcer.npz} RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3eb78af32779b5fabbb92e7cdbdeaaa34f5f8ad1085e213b101165665c5ce4cb
3
- size 9472
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:26f2d1a9e3b6fe453cf5fc8191de26cbfae6276c5b0f7c376c6a0f3c35867f83
3
+ size 16794
speaker_embeddings/{announcer_coarse_prompt.npy → de_speaker_0.npz} RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2c77d5e1f9ab39e489d27628ab26dfae7a8b4cae4ba72658a1a94927f7ff5132
3
- size 3128
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:008d7f3d0a52305a80c1abce26ccf4120181554a24055a0581894819b14f998d
3
+ size 31940
speaker_embeddings/de_speaker_0_fine_prompt.npy DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:a2421bcbeb7fadfcf1c0b33e38e316474d4a95139d4dd0b3d861e72c8fd77c36
3
- size 18816
 
 
 
 
speaker_embeddings/de_speaker_0_semantic_prompt.npy DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:44e5539dbcd158a2471c59b46cde7f0564d108cd2fd935e3664b2ec733ad4393
3
- size 3240
 
 
 
 
speaker_embeddings/{announcer_fine_prompt.npy → de_speaker_1.npz} RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7aac73cd2a14c1939a718aeb48b064d149b39f773f1dcc9b93be6f79ebd33755
3
- size 12128
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b5bb2ac34fa466f5d6804f48f51658d7b7d8d91ce7139d34c717c917578858fb
3
+ size 31940
speaker_embeddings/de_speaker_1_coarse_prompt.npy DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:6ac93157e39cd0fa7a5e9d0404d6adcb3daaec8e820b42b72b96de62e19ca89b
3
- size 9472
 
 
 
 
speaker_embeddings/de_speaker_1_fine_prompt.npy DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:9f8eaca4b732dd3264213ac387f4c91f83a574563b0d72368b237df03fe92b4d
3
- size 18816
 
 
 
 
speaker_embeddings/de_speaker_1_semantic_prompt.npy DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:98cde60e36a6265d6534e4c6422436f201a9bfcdc87f9817d6faf6ab4f22554b
3
- size 3240
 
 
 
 
speaker_embeddings/{announcer_semantic_prompt.npy → de_speaker_2.npz} RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f5564642cbd84db6f4d1d8a522bd26329b4f4cd8cd81e1965b90baf1ee80c7ff
3
- size 1126
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1dedc8ab1949653480223f0c0cf3ebd20406d39b52e19908d32275eb8cfaf4b9
3
+ size 23516
speaker_embeddings/de_speaker_2_coarse_prompt.npy DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:fd5e9d07b0480dda2c3661de1da0671f34419c029c8e7410705139a38fb133d3
3
- size 6944
 
 
 
 
speaker_embeddings/de_speaker_2_fine_prompt.npy DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:4f11b22a8a24428ca0114e4fcc770c0ca554376de95be7ac5ac560ae4f1988fb
3
- size 13760
 
 
 
 
speaker_embeddings/de_speaker_2_semantic_prompt.npy DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:8efe5707a724632900ab5cb274ffdbac0d39fd6dda1be49833d63311df478ef3
3
- size 2400
 
 
 
 
speaker_embeddings/de_speaker_3.npz ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c5abe325e6306a7f96725fcc6186c0eb147d2f068ce14b863e086cbf52b1986e
3
+ size 29060
speaker_embeddings/de_speaker_3_coarse_prompt.npy DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:bf0fb48dd18c79996fc800abbd3407dd967b21a36bda695584e29d302ead274a
3
- size 8608
 
 
 
 
speaker_embeddings/de_speaker_3_fine_prompt.npy DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:229455388c628e9d168ad11940041b15ed3b40f724ab3a4747f6cb38b2f5230a
3
- size 17088
 
 
 
 
speaker_embeddings/de_speaker_3_semantic_prompt.npy DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:88fee5c6b974dbfb1168b55f73990be270847a91a2e7895d298b188f3ad7da9f
3
- size 2952
 
 
 
 
speaker_embeddings/de_speaker_4.npz ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:91d102ad045aabc996f487d0d4f0b3fd289ef2da200d1df289cf5da298d23796
3
+ size 20316
speaker_embeddings/de_speaker_4_coarse_prompt.npy DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:0268e63ef8aa7c6113af4a840c3581c08edea0eacec8aaa7d52da8012d8c16f5
3
- size 5984
 
 
 
 
speaker_embeddings/de_speaker_4_fine_prompt.npy DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:21c41cce8756afcd8b690ad8701e35f33b4c0be3c63bae5f6ebbc10e5cb3c150
3
- size 11840
 
 
 
 
speaker_embeddings/de_speaker_4_semantic_prompt.npy DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:a03e84c7f1f4dd97f033d999fea8eb76c4dde6883e1dae67303b6a46bdb57803
3
- size 2080
 
 
 
 
speaker_embeddings/de_speaker_5.npz ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8aa116b450c74c60ef43d1fd141fe961e23ebeafdcb57991b22ae4a08c62cf44
3
+ size 35084
speaker_embeddings/de_speaker_5_coarse_prompt.npy DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:3f4272d4c3928264a36a406b9c0d306db99316180dca8e96504c93244fc61d96
3
- size 10416
 
 
 
 
speaker_embeddings/de_speaker_5_fine_prompt.npy DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:dac52541ccb321598997fe0e27ebadf5540eb6e53a8b3a614d7cabfcbae4b2d0
3
- size 20704
 
 
 
 
speaker_embeddings/de_speaker_5_semantic_prompt.npy DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:412b3a1f45525390e84bd2109bb86af782da2245adcbdd8803c1b362a311075c
3
- size 3552
 
 
 
 
speaker_embeddings/de_speaker_6.npz ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0f95bd28bc7382b7294c0bb187b18873aa9c050b3fe5793166c547200c8e2da9
3
+ size 31724
speaker_embeddings/de_speaker_6_coarse_prompt.npy DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:bc029718234023df88f9ae4ea830a90115bd2256b10fe8c3c725483392c0f6c2
3
- size 9408
 
 
 
 
speaker_embeddings/de_speaker_6_fine_prompt.npy DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:3414b015ad3567a2590f5b044f3d2043270bef8b03cb1348b7265d21bbca2299
3
- size 18688
 
 
 
 
speaker_embeddings/de_speaker_6_semantic_prompt.npy DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:2300ace5fda24f16a27b345a6f54c19e2e2363808cac0a58bac12518b4c8f77d
3
- size 3216
 
 
 
 
speaker_embeddings/{v2/es_speaker_4_semantic_prompt.npy → de_speaker_7.npz} RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f31358e73695e3ba4db7dc6bccae07fe87bf3ae08ba15fd3348474f01293c759
3
- size 2384
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:332c5aee851c0544e1ad587fbc477b8d4eb28e852192fcd969d97c894b028a2b
3
+ size 59348
speaker_embeddings/de_speaker_7_coarse_prompt.npy DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:cd86cb193cb39a077a2cb2540af2953ce7f2f480ec3129c5191e730b87329493
3
- size 17696
 
 
 
 
speaker_embeddings/de_speaker_7_fine_prompt.npy DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:6e97d71d8a7120bff91f08ccf1d0e6d1e8b6983642d56dad0cbe0f8dc2554343
3
- size 35264
 
 
 
 
speaker_embeddings/de_speaker_7_semantic_prompt.npy DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:7be7d81cb55364f3db979ce92315e2e64517203b9300caca6414970ec81c220b
3
- size 5976
 
 
 
 
speaker_embeddings/de_speaker_8.npz ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a0eefea2a0d702177f44df4b218b950119726c041cb505e1df36ab0fc0651018
3
+ size 25116
speaker_embeddings/de_speaker_8_coarse_prompt.npy DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:06efd00181d007e30b7b7bede472ea50e9f7c61aa7b76074884d26eec8d965f7
3
- size 7424
 
 
 
 
speaker_embeddings/de_speaker_8_fine_prompt.npy DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:f566f926840a3e70e115fc41b0bf4c3f658b1b23e8583e7492d7f0ae13423ac5
3
- size 14720
 
 
 
 
speaker_embeddings/de_speaker_8_semantic_prompt.npy DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:1919388fdd9b0e236e7bdeef4f6ad1416c7b0e49daf72cf5e064b2e2106584aa
3
- size 2560
 
 
 
 
speaker_embeddings/de_speaker_9.npz ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:189e941a182411853351c56e422d51a4a8fad20f1f8b8f396042bb2ada3cceb2
3
+ size 22180
speaker_embeddings/de_speaker_9_coarse_prompt.npy DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:97012e37b1d51da9b2aebfb521b568713042cb4e086367dc5f2558c0b6629486
3
- size 6544
 
 
 
 
speaker_embeddings/de_speaker_9_fine_prompt.npy DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:f455a59e0d759103c7d8802bccef33cf0cafbf9122605179278d6f7ff302acdf
3
- size 12960
 
 
 
 
speaker_embeddings/de_speaker_9_semantic_prompt.npy DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:8efede4bec02ec98fc470dc53ca00154fea57f895a931ef6f44b1e9621b18ad2
3
- size 2264
 
 
 
 
speaker_embeddings/en_speaker_0.npz ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eb130b14872cc53381bdb867cee71c26a6d116af81dbf2542f3f44d11b8aaf3f
3
+ size 22396
speaker_embeddings/en_speaker_0_coarse_prompt.npy DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:1d91b5e26a8c703a7764b21570d8cc94aee3bb043a407c3ace89976f701ddf8f
3
- size 6608
 
 
 
 
speaker_embeddings/en_speaker_0_fine_prompt.npy DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:24bebee667439786f17048d4ec3f36460d6d9f9f59495b3076a116e6e3f71f6e
3
- size 13088
 
 
 
 
speaker_embeddings/en_speaker_0_semantic_prompt.npy DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:01f0c8e96aee83c19514700491be4326c5a1194631cdd486e1d4b76e4d0c0de0
3
- size 2288
 
 
 
 
speaker_embeddings/en_speaker_1.npz ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3cdc113954acb3839e9112437a029d482925236bce91294803a42e3f1f493aea
3
+ size 18396