Hugging Face's logo

mlx-community
/
bark

Safetensors
bark
Model card Files
xet
 Community
roboalchemist commited on
Commit
7656006
·
verified ·
1 Parent(s): 6e45934

Upload folder using huggingface_hub

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. README.md +20 -0
  2. config.json +66 -0
  3. fine_acoustics.safetensors +3 -0
  4. generation_config.json +172 -0
  5. model.safetensors +3 -0
  6. speaker_embeddings/announcer.npz +3 -0
  7. speaker_embeddings/announcer_coarse_prompt.npy +3 -0
  8. speaker_embeddings/announcer_fine_prompt.npy +3 -0
  9. speaker_embeddings/announcer_semantic_prompt.npy +3 -0
  10. speaker_embeddings/de_speaker_0.npz +3 -0
  11. speaker_embeddings/de_speaker_0_coarse_prompt.npy +3 -0
  12. speaker_embeddings/de_speaker_0_fine_prompt.npy +3 -0
  13. speaker_embeddings/de_speaker_0_semantic_prompt.npy +3 -0
  14. speaker_embeddings/de_speaker_1.npz +3 -0
  15. speaker_embeddings/de_speaker_1_coarse_prompt.npy +3 -0
  16. speaker_embeddings/de_speaker_1_fine_prompt.npy +3 -0
  17. speaker_embeddings/de_speaker_1_semantic_prompt.npy +3 -0
  18. speaker_embeddings/de_speaker_2.npz +3 -0
  19. speaker_embeddings/de_speaker_2_coarse_prompt.npy +3 -0
  20. speaker_embeddings/de_speaker_2_fine_prompt.npy +3 -0
  21. speaker_embeddings/de_speaker_2_semantic_prompt.npy +3 -0
  22. speaker_embeddings/de_speaker_3.npz +3 -0
  23. speaker_embeddings/de_speaker_3_coarse_prompt.npy +3 -0
  24. speaker_embeddings/de_speaker_3_fine_prompt.npy +3 -0
  25. speaker_embeddings/de_speaker_3_semantic_prompt.npy +3 -0
  26. speaker_embeddings/de_speaker_4.npz +3 -0
  27. speaker_embeddings/de_speaker_4_coarse_prompt.npy +3 -0
  28. speaker_embeddings/de_speaker_4_fine_prompt.npy +3 -0
  29. speaker_embeddings/de_speaker_4_semantic_prompt.npy +3 -0
  30. speaker_embeddings/de_speaker_5.npz +3 -0
  31. speaker_embeddings/de_speaker_5_coarse_prompt.npy +3 -0
  32. speaker_embeddings/de_speaker_5_fine_prompt.npy +3 -0
  33. speaker_embeddings/de_speaker_5_semantic_prompt.npy +3 -0
  34. speaker_embeddings/de_speaker_6.npz +3 -0
  35. speaker_embeddings/de_speaker_6_coarse_prompt.npy +3 -0
  36. speaker_embeddings/de_speaker_6_fine_prompt.npy +3 -0
  37. speaker_embeddings/de_speaker_6_semantic_prompt.npy +3 -0
  38. speaker_embeddings/de_speaker_7.npz +3 -0
  39. speaker_embeddings/de_speaker_7_coarse_prompt.npy +3 -0
  40. speaker_embeddings/de_speaker_7_fine_prompt.npy +3 -0
  41. speaker_embeddings/de_speaker_7_semantic_prompt.npy +3 -0
  42. speaker_embeddings/de_speaker_8.npz +3 -0
  43. speaker_embeddings/de_speaker_8_coarse_prompt.npy +3 -0
  44. speaker_embeddings/de_speaker_8_fine_prompt.npy +3 -0
  45. speaker_embeddings/de_speaker_8_semantic_prompt.npy +3 -0
  46. speaker_embeddings/de_speaker_9.npz +3 -0
  47. speaker_embeddings/de_speaker_9_coarse_prompt.npy +3 -0
  48. speaker_embeddings/de_speaker_9_fine_prompt.npy +3 -0
  49. speaker_embeddings/de_speaker_9_semantic_prompt.npy +3 -0
  50. speaker_embeddings/en_speaker_0.npz +3 -0
README.md ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ # mlx-community/bark
2
+
3
+ This model was converted to MLX format from [`suno/bark`](https://huggingface.co/suno/bark) using mlx-audio version **0.2.8**.
4
+
5
+ Bark is a transformer-based text-to-audio model created by [Suno](https://www.suno.ai).
6
+ It generates highly realistic, multilingual speech as well as music, background noise, and simple sound effects.
7
+
8
+ ## Use with mlx-audio
9
+
10
+ ```bash
11
+ pip install -U mlx-audio
12
+ python -m mlx_audio.tts.generate --model mlx-community/bark --text "Hello, this is a test."
13
+ ```
14
+
15
+ ## Model Details
16
+
17
+ - Architecture: Bark (semantic + coarse acoustics + fine acoustics + encodec)
18
+ - Parameters: ~1B (full model)
19
+ - Languages: English, German, Spanish, French, Hindi, Italian, Japanese, Korean, Polish, Portuguese, Russian, Turkish, Chinese
20
+ - Sample rate: 24kHz
config.json ADDED
@@ -0,0 +1,66 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "BarkModel"
4
+ ],
5
+ "model_type": "bark",
6
+ "model_size": "base",
7
+ "initializer_range": 0.02,
8
+ "torch_dtype": "float32",
9
+ "semantic_config": {
10
+ "model_type": "semantic",
11
+ "architectures": [
12
+ "BarkSemanticModel"
13
+ ],
14
+ "n_layer": 24,
15
+ "n_head": 16,
16
+ "n_embd": 1024,
17
+ "input_vocab_size": 129600,
18
+ "output_vocab_size": 10048,
19
+ "block_size": 1024,
20
+ "bias": false,
21
+ "dropout": 0.0
22
+ },
23
+ "coarse_acoustics_config": {
24
+ "model_type": "coarse_acoustics",
25
+ "architectures": [
26
+ "BarkCoarseModel"
27
+ ],
28
+ "n_layer": 24,
29
+ "n_head": 16,
30
+ "n_embd": 1024,
31
+ "input_vocab_size": 12096,
32
+ "output_vocab_size": 12096,
33
+ "block_size": 1024,
34
+ "bias": false,
35
+ "dropout": 0.0
36
+ },
37
+ "fine_acoustics_config": {
38
+ "model_type": "fine_acoustics",
39
+ "architectures": [
40
+ "BarkFineModel"
41
+ ],
42
+ "n_layer": 24,
43
+ "n_head": 16,
44
+ "n_embd": 1024,
45
+ "input_vocab_size": 1056,
46
+ "output_vocab_size": 1056,
47
+ "block_size": 1024,
48
+ "bias": true,
49
+ "dropout": 0.0,
50
+ "n_codes_total": 8,
51
+ "n_codes_given": 1
52
+ },
53
+ "codec_config": {
54
+ "model_type": "encodec",
55
+ "architectures": [
56
+ "EncodecModel"
57
+ ],
58
+ "_name_or_path": "facebook/encodec_24khz",
59
+ "sample_rate": 24000,
60
+ "audio_channels": 1,
61
+ "normalize": false,
62
+ "use_causal_conv": true
63
+ },
64
+ "sample_rate": 24000,
65
+ "block_size": 1024
66
+ }
fine_acoustics.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f5a3a4d14c3cc747264667b46e27d3939ed02d1d9c94dd60cd647349f4009951
3
+ size 1247181832
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
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dbbc2b3a341bed372bbcce8f151c5d6443cd3a4707dcc27ed8ea353426191b9a
3
+ size 3188955960
speaker_embeddings/announcer.npz ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:36b1f9b275b45872141e510bb8f426e93e3ac5c4be88ada48a6fce864fd3434e
3
+ size 16794
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.npz ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d6f05bfc4088e95e5f9b9484f87c33290356e9c5162f714e1b448b57b6c53093
3
+ size 31940
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.npz ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ea23b69b1f49cca9c6dcc4a5f4441e8f8afc58343d89535a19d6c5556cb4ae78
3
+ size 31940
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.npz ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:319e727c123f86aa374996bdc3d1ec5c2a8c9cbb31113afd6dc0ea968dbc0c01
3
+ size 23516
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.npz ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed06053e305e9e317a34aeb9c3f899efefc56873ae6297fa25b041870b62bfc3
3
+ size 29060
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.npz ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b70db3fdfe0065dfdf59dd072cf6f2a66369ed7b631114d6ef0ed36dbe4cd65b
3
+ size 20316
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.npz ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:26a0c0572aa47e7d50eedcd3dd1877fc786f61416e10f3b994fddf3f5e8f0249
3
+ size 35084
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.npz ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf020dee59544b5fb412df4061cf7d59d82cfcff399a51a91b7fe1a5532692cc
3
+ size 31724
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.npz ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c953d12c57918d5d5da53bfe83ea8aefad76c7c7af9afc57c1fdfa9d8b5aa915
3
+ size 59348
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.npz ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a64f11b871019514d1085c863f299cbb4dbb5869947e0b4f4da902f5ee5e2cf7
3
+ size 25116
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.npz ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:10536e59b4b44bbc1571e7069840145c5fe82561060abed97412a1420fe2dbba
3
+ size 22180
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.npz ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:62b55b4a7a9789e4f373d1bd94bee11252d77424842634bb95ed287e9538c8b7
3
+ size 22396