Spaces:
Runtime error
Runtime error
Create speakers.json
Browse files- speakers.json +185 -0
speakers.json
ADDED
@@ -0,0 +1,185 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
"en": {
|
2 |
+
"ek1": {
|
3 |
+
"tacotron2": {
|
4 |
+
"description": "EK1 en-rp tacotron2 by NMStoker",
|
5 |
+
"github_rls_url": "https://coqui.gateway.scarf.sh/v0.6.1_models/tts_models--en--ek1--tacotron2.zip",
|
6 |
+
"default_vocoder": "vocoder_models/en/ek1/wavegrad",
|
7 |
+
"commit": "c802255",
|
8 |
+
"license": "apache 2.0"
|
9 |
+
}
|
10 |
+
},
|
11 |
+
"ljspeech": {
|
12 |
+
"tacotron2-DDC": {
|
13 |
+
"description": "Tacotron2 with Double Decoder Consistency.",
|
14 |
+
"github_rls_url": "https://coqui.gateway.scarf.sh/v0.6.1_models/tts_models--en--ljspeech--tacotron2-DDC.zip",
|
15 |
+
"default_vocoder": "vocoder_models/en/ljspeech/hifigan_v2",
|
16 |
+
"commit": "bae2ad0f",
|
17 |
+
"author": "Eren Gölge @erogol",
|
18 |
+
"license": "apache 2.0",
|
19 |
+
"contact": "egolge@coqui.com"
|
20 |
+
},
|
21 |
+
"tacotron2-DDC_ph": {
|
22 |
+
"description": "Tacotron2 with Double Decoder Consistency with phonemes.",
|
23 |
+
"github_rls_url": "https://coqui.gateway.scarf.sh/v0.6.1_models/tts_models--en--ljspeech--tacotron2-DDC_ph.zip",
|
24 |
+
"default_vocoder": "vocoder_models/en/ljspeech/univnet",
|
25 |
+
"commit": "3900448",
|
26 |
+
"author": "Eren Gölge @erogol",
|
27 |
+
"license": "apache 2.0",
|
28 |
+
"contact": "egolge@coqui.com"
|
29 |
+
},
|
30 |
+
"glow-tts": {
|
31 |
+
"description": "",
|
32 |
+
"github_rls_url": "https://coqui.gateway.scarf.sh/v0.6.1_models/tts_models--en--ljspeech--glow-tts.zip",
|
33 |
+
"stats_file": null,
|
34 |
+
"default_vocoder": "vocoder_models/en/ljspeech/multiband-melgan",
|
35 |
+
"commit": "",
|
36 |
+
"author": "Eren Gölge @erogol",
|
37 |
+
"license": "MPL",
|
38 |
+
"contact": "egolge@coqui.com"
|
39 |
+
},
|
40 |
+
"speedy-speech": {
|
41 |
+
"description": "Speedy Speech model trained on LJSpeech dataset using the Alignment Network for learning the durations.",
|
42 |
+
"github_rls_url": "https://coqui.gateway.scarf.sh/v0.6.1_models/tts_models--en--ljspeech--speedy-speech.zip",
|
43 |
+
"stats_file": null,
|
44 |
+
"default_vocoder": "vocoder_models/en/ljspeech/hifigan_v2",
|
45 |
+
"commit": "4581e3d",
|
46 |
+
"author": "Eren Gölge @erogol",
|
47 |
+
"license": "apache 2.0",
|
48 |
+
"contact": "egolge@coqui.com"
|
49 |
+
},
|
50 |
+
"tacotron2-DCA": {
|
51 |
+
"description": "",
|
52 |
+
"github_rls_url": "https://coqui.gateway.scarf.sh/v0.6.1_models/tts_models--en--ljspeech--tacotron2-DCA.zip",
|
53 |
+
"default_vocoder": "vocoder_models/en/ljspeech/multiband-melgan",
|
54 |
+
"commit": "",
|
55 |
+
"author": "Eren Gölge @erogol",
|
56 |
+
"license": "MPL",
|
57 |
+
"contact": "egolge@coqui.com"
|
58 |
+
},
|
59 |
+
"vits": {
|
60 |
+
"description": "VITS is an End2End TTS model trained on LJSpeech dataset with phonemes.",
|
61 |
+
"github_rls_url": "https://coqui.gateway.scarf.sh/v0.6.1_models/tts_models--en--ljspeech--vits.zip",
|
62 |
+
"default_vocoder": null,
|
63 |
+
"commit": "3900448",
|
64 |
+
"author": "Eren Gölge @erogol",
|
65 |
+
"license": "apache 2.0",
|
66 |
+
"contact": "egolge@coqui.com"
|
67 |
+
},
|
68 |
+
"vits--neon": {
|
69 |
+
"github_rls_url": "https://coqui.gateway.scarf.sh/v0.8.0_models/tts_models--en--ljspeech--vits.zip",
|
70 |
+
"default_vocoder": null,
|
71 |
+
"author": "@NeonGeckoCom",
|
72 |
+
"license": "bsd-3-clause",
|
73 |
+
"contact": null,
|
74 |
+
"commit": null
|
75 |
+
},
|
76 |
+
"fast_pitch": {
|
77 |
+
"description": "FastPitch model trained on LJSpeech using the Aligner Network",
|
78 |
+
"github_rls_url": "https://coqui.gateway.scarf.sh/v0.6.1_models/tts_models--en--ljspeech--fast_pitch.zip",
|
79 |
+
"default_vocoder": "vocoder_models/en/ljspeech/hifigan_v2",
|
80 |
+
"commit": "b27b3ba",
|
81 |
+
"author": "Eren Gölge @erogol",
|
82 |
+
"license": "apache 2.0",
|
83 |
+
"contact": "egolge@coqui.com"
|
84 |
+
},
|
85 |
+
"overflow": {
|
86 |
+
"description": "Overflow model trained on LJSpeech",
|
87 |
+
"github_rls_url": "https://coqui.gateway.scarf.sh/v0.10.0_models/tts_models--en--ljspeech--overflow.zip",
|
88 |
+
"default_vocoder": "vocoder_models/en/ljspeech/hifigan_v2",
|
89 |
+
"commit": "3b1a28f",
|
90 |
+
"author": "Eren Gölge @erogol",
|
91 |
+
"license": "apache 2.0",
|
92 |
+
"contact": "egolge@coqui.ai"
|
93 |
+
},
|
94 |
+
"neural_hmm": {
|
95 |
+
"description": "Neural HMM model trained on LJSpeech",
|
96 |
+
"github_rls_url": "https://coqui.gateway.scarf.sh/v0.11.0_models/tts_models--en--ljspeech--neural_hmm.zip",
|
97 |
+
"default_vocoder": "vocoder_models/en/ljspeech/hifigan_v2",
|
98 |
+
"commit": "3b1a28f",
|
99 |
+
"author": "Shivam Metha @shivammehta25",
|
100 |
+
"license": "apache 2.0",
|
101 |
+
"contact": "d83ee8fe45e3c0d776d4a865aca21d7c2ac324c4"
|
102 |
+
}
|
103 |
+
},
|
104 |
+
"vctk": {
|
105 |
+
"vits": {
|
106 |
+
"description": "VITS End2End TTS model trained on VCTK dataset with 109 different speakers with EN accent.",
|
107 |
+
"github_rls_url": "https://coqui.gateway.scarf.sh/v0.6.1_models/tts_models--en--vctk--vits.zip",
|
108 |
+
"default_vocoder": null,
|
109 |
+
"commit": "3900448",
|
110 |
+
"author": "Eren @erogol",
|
111 |
+
"license": "apache 2.0",
|
112 |
+
"contact": "egolge@coqui.ai"
|
113 |
+
},
|
114 |
+
"fast_pitch": {
|
115 |
+
"description": "FastPitch model trained on VCTK dataseset.",
|
116 |
+
"github_rls_url": "https://coqui.gateway.scarf.sh/v0.6.1_models/tts_models--en--vctk--fast_pitch.zip",
|
117 |
+
"default_vocoder": null,
|
118 |
+
"commit": "bdab788d",
|
119 |
+
"author": "Eren @erogol",
|
120 |
+
"license": "CC BY-NC-ND 4.0",
|
121 |
+
"contact": "egolge@coqui.ai"
|
122 |
+
}
|
123 |
+
},
|
124 |
+
"sam": {
|
125 |
+
"tacotron-DDC": {
|
126 |
+
"description": "Tacotron2 with Double Decoder Consistency trained with Aceenture's Sam dataset.",
|
127 |
+
"github_rls_url": "https://coqui.gateway.scarf.sh/v0.6.1_models/tts_models--en--sam--tacotron-DDC.zip",
|
128 |
+
"default_vocoder": "vocoder_models/en/sam/hifigan_v2",
|
129 |
+
"commit": "bae2ad0f",
|
130 |
+
"author": "Eren Gölge @erogol",
|
131 |
+
"license": "apache 2.0",
|
132 |
+
"contact": "egolge@coqui.com"
|
133 |
+
}
|
134 |
+
},
|
135 |
+
"blizzard2013": {
|
136 |
+
"capacitron-t2-c50": {
|
137 |
+
"description": "Capacitron additions to Tacotron 2 with Capacity at 50 as in https://arxiv.org/pdf/1906.03402.pdf",
|
138 |
+
"github_rls_url": "https://coqui.gateway.scarf.sh/v0.7.0_models/tts_models--en--blizzard2013--capacitron-t2-c50.zip",
|
139 |
+
"commit": "d6284e7",
|
140 |
+
"default_vocoder": "vocoder_models/en/blizzard2013/hifigan_v2",
|
141 |
+
"author": "Adam Froghyar @a-froghyar",
|
142 |
+
"license": "apache 2.0",
|
143 |
+
"contact": "adamfroghyar@gmail.com"
|
144 |
+
},
|
145 |
+
"capacitron-t2-c150_v2": {
|
146 |
+
"description": "Capacitron additions to Tacotron 2 with Capacity at 150 as in https://arxiv.org/pdf/1906.03402.pdf",
|
147 |
+
"github_rls_url": "https://coqui.gateway.scarf.sh/v0.7.1_models/tts_models--en--blizzard2013--capacitron-t2-c150_v2.zip",
|
148 |
+
"commit": "a67039d",
|
149 |
+
"default_vocoder": "vocoder_models/en/blizzard2013/hifigan_v2",
|
150 |
+
"author": "Adam Froghyar @a-froghyar",
|
151 |
+
"license": "apache 2.0",
|
152 |
+
"contact": "adamfroghyar@gmail.com"
|
153 |
+
}
|
154 |
+
},
|
155 |
+
"multi-dataset": {
|
156 |
+
"tortoise-v2": {
|
157 |
+
"description": "Tortoise tts model https://github.com/neonbjb/tortoise-tts",
|
158 |
+
"github_rls_url": [
|
159 |
+
"https://coqui.gateway.scarf.sh/v0.14.1_models/autoregressive.pth",
|
160 |
+
"https://coqui.gateway.scarf.sh/v0.14.1_models/clvp2.pth",
|
161 |
+
"https://coqui.gateway.scarf.sh/v0.14.1_models/cvvp.pth",
|
162 |
+
"https://coqui.gateway.scarf.sh/v0.14.1_models/diffusion_decoder.pth",
|
163 |
+
"https://coqui.gateway.scarf.sh/v0.14.1_models/rlg_auto.pth",
|
164 |
+
"https://coqui.gateway.scarf.sh/v0.14.1_models/rlg_diffuser.pth",
|
165 |
+
"https://coqui.gateway.scarf.sh/v0.14.1_models/vocoder.pth",
|
166 |
+
"https://coqui.gateway.scarf.sh/v0.14.1_models/mel_norms.pth",
|
167 |
+
"https://coqui.gateway.scarf.sh/v0.14.1_models/config.json"
|
168 |
+
],
|
169 |
+
"commit": "c1875f6",
|
170 |
+
"default_vocoder": null,
|
171 |
+
"author": "@neonbjb - James Betker, @manmay-nakhashi Manmay Nakhashi",
|
172 |
+
"license": "apache 2.0"
|
173 |
+
}
|
174 |
+
},
|
175 |
+
"jenny": {
|
176 |
+
"jenny": {
|
177 |
+
"description": "VITS model trained with Jenny(Dioco) dataset. Named as Jenny as demanded by the license. Original URL for the model https://www.kaggle.com/datasets/noml4u/tts-models--en--jenny-dioco--vits",
|
178 |
+
"github_rls_url": "https://coqui.gateway.scarf.sh/v0.14.0_models/tts_models--en--jenny--jenny.zip",
|
179 |
+
"default_vocoder": null,
|
180 |
+
"commit": "ba40a1c",
|
181 |
+
"license": "custom - see https://github.com/dioco-group/jenny-tts-dataset#important",
|
182 |
+
"author": "@noml4u"
|
183 |
+
}
|
184 |
+
}
|
185 |
+
},
|