Medix-AI/coqui-tts
Medix-AI
/
coqui-tts
mirror of https://github.com/coqui-ai/TTS.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Add the models released with v0.2.0

This commit is contained in:
Eren Gölge 2021-08-10 15:46:06 +00:00
parent 39004484b9
commit 09ed8426e8
1 changed files with 104 additions and 61 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

165
TTS/.models.json
View File

@ -1,7 +1,7 @@
{ {
"tts_models":{ "tts_models": {
"en":{ "en": {
"ek1":{ "ek1": {
"tacotron2": { "tacotron2": {
"description": "EK1 en-rp tacotron2 by NMStoker", "description": "EK1 en-rp tacotron2 by NMStoker",
"github_rls_url": "https://github.com/coqui-ai/TTS/releases/download/v0.1.0/tts_models--en--ek1--tacotron2.zip", "github_rls_url": "https://github.com/coqui-ai/TTS/releases/download/v0.1.0/tts_models--en--ek1--tacotron2.zip",
@ -9,7 +9,7 @@
"commit": "c802255" "commit": "c802255"
} }
}, },
"ljspeech":{ "ljspeech": {
"tacotron2-DDC": { "tacotron2-DDC": {
"description": "Tacotron2 with Double Decoder Consistency.", "description": "Tacotron2 with Double Decoder Consistency.",
"github_rls_url": "https://github.com/coqui-ai/TTS/releases/download/v0.0.12/tts_models--en--ljspeech--tacotron2-DDC.zip", "github_rls_url": "https://github.com/coqui-ai/TTS/releases/download/v0.0.12/tts_models--en--ljspeech--tacotron2-DDC.zip",
@ -17,9 +17,18 @@
"commit": "bae2ad0f", "commit": "bae2ad0f",
"author": "Eren Gölge @erogol", "author": "Eren Gölge @erogol",
"license": "", "license": "",
"contact":"egolge@coqui.com" "contact": "egolge@coqui.com"
}, },
"glow-tts":{ "tacotron2-DDC_ph": {
"description": "Tacotron2 with Double Decoder Consistency with phonemes.",
"github_rls_url": "https://github.com/coqui-ai/TTS/releases/download/v0.2.0/tts_models--en--ljspeech--tacotronDDC_ph.zip",
"default_vocoder": "vocoder_models/en/ljspeech/univnet",
"commit": "3900448",
"author": "Eren Gölge @erogol",
"license": "",
"contact": "egolge@coqui.com"
},
"glow-tts": {
"description": "", "description": "",
"github_rls_url": "https://github.com/coqui-ai/TTS/releases/download/v0.0.9/tts_models--en--ljspeech--glow-tts.zip", "github_rls_url": "https://github.com/coqui-ai/TTS/releases/download/v0.0.9/tts_models--en--ljspeech--glow-tts.zip",
"stats_file": null, "stats_file": null,
@ -27,7 +36,7 @@
"commit": "", "commit": "",
"author": "Eren Gölge @erogol", "author": "Eren Gölge @erogol",
"license": "MPL", "license": "MPL",
"contact":"egolge@coqui.com" "contact": "egolge@coqui.com"
}, },
"tacotron2-DCA": { "tacotron2-DCA": {
"description": "", "description": "",
@ -36,19 +45,28 @@
"commit": "", "commit": "",
"author": "Eren Gölge @erogol", "author": "Eren Gölge @erogol",
"license": "MPL", "license": "MPL",
"contact":"egolge@coqui.com" "contact": "egolge@coqui.com"
}, },
"speedy-speech-wn":{ "speedy-speech-wn": {
"description": "Speedy Speech model with wavenet decoder.", "description": "Speedy Speech model with wavenet decoder.",
"github_rls_url": "https://github.com/coqui-ai/TTS/releases/download/v0.1.0/tts_models--en--ljspeech--speedy-speech-wn.zip", "github_rls_url": "https://github.com/coqui-ai/TTS/releases/download/v0.1.0/tts_models--en--ljspeech--speedy-speech-wn.zip",
"default_vocoder": "vocoder_models/en/ljspeech/multiband-melgan", "default_vocoder": "vocoder_models/en/ljspeech/multiband-melgan",
"commit": "77b6145", "commit": "77b6145",
"author": "Eren Gölge @erogol", "author": "Eren Gölge @erogol",
"license": "MPL", "license": "MPL",
"contact":"egolge@coqui.com" "contact": "egolge@coqui.com"
},
"vits": {
"description": "VITS is an End2End TTS model trained on LJSpeech dataset with phonemes.",
"github_rls_url": "https://github.com/coqui-ai/TTS/releases/download/v0.2.0/tts_models--en--ljspeech--vits.zip",
"default_vocoder": null,
"commit": "3900448",
"author": "Eren Gölge @erogol",
"license": "",
"contact": "egolge@coqui.com"
} }
}, },
"vctk":{ "vctk": {
"sc-glow-tts": { "sc-glow-tts": {
"description": "Multi-Speaker Transformers based SC-Glow model from https://arxiv.org/abs/2104.05557.", "description": "Multi-Speaker Transformers based SC-Glow model from https://arxiv.org/abs/2104.05557.",
"github_rls_url": "https://github.com/coqui-ai/TTS/releases/download/v0.1.0/tts_models--en--vctk--sc-glow-tts.zip", "github_rls_url": "https://github.com/coqui-ai/TTS/releases/download/v0.1.0/tts_models--en--vctk--sc-glow-tts.zip",
@ -56,12 +74,19 @@
"commit": "b531fa69", "commit": "b531fa69",
"author": "Edresson Casanova", "author": "Edresson Casanova",
"license": "", "license": "",
"contact":"" "contact": ""
},
"vits": {
"description": "VITS End2End TTS model trained on VCTK dataset with 109 different speakers with EN accent.",
"github_rls_url": "https://github.com/coqui-ai/TTS/releases/download/v0.2.0/tts_models--en--vctk--vits.zip",
"default_vocoder": null,
"commit": "3900448",
"author": "Eren @erogol",
"license": "",
"contact": "egolge@coqui.ai"
} }
}, },
"sam":{ "sam": {
"tacotron-DDC": { "tacotron-DDC": {
"description": "Tacotron2 with Double Decoder Consistency trained with Aceenture's Sam dataset.", "description": "Tacotron2 with Double Decoder Consistency trained with Aceenture's Sam dataset.",
"github_rls_url": "https://github.com/coqui-ai/TTS/releases/download/v0.0.13/tts_models--en--sam--tacotron_DDC.zip", "github_rls_url": "https://github.com/coqui-ai/TTS/releases/download/v0.0.13/tts_models--en--sam--tacotron_DDC.zip",
@ -69,37 +94,37 @@
"commit": "bae2ad0f", "commit": "bae2ad0f",
"author": "Eren Gölge @erogol", "author": "Eren Gölge @erogol",
"license": "", "license": "",
"contact":"egolge@coqui.com" "contact": "egolge@coqui.com"
} }
} }
}, },
"es":{ "es": {
"mai":{ "mai": {
"tacotron2-DDC":{ "tacotron2-DDC": {
"github_rls_url": "https://github.com/coqui-ai/TTS/releases/download/v0.0.9/tts_models--es--mai--tacotron2-DDC.zip", "github_rls_url": "https://github.com/coqui-ai/TTS/releases/download/v0.0.9/tts_models--es--mai--tacotron2-DDC.zip",
"default_vocoder": "vocoder_models/universal/libri-tts/fullband-melgan", "default_vocoder": "vocoder_models/universal/libri-tts/fullband-melgan",
"commit": "", "commit": "",
"author": "Eren Gölge @erogol", "author": "Eren Gölge @erogol",
"license": "MPL", "license": "MPL",
"contact":"egolge@coqui.com" "contact": "egolge@coqui.com"
} }
} }
}, },
"fr":{ "fr": {
"mai":{ "mai": {
"tacotron2-DDC":{ "tacotron2-DDC": {
"github_rls_url": "https://github.com/coqui-ai/TTS/releases/download/v0.0.9/tts_models--fr--mai--tacotron2-DDC.zip", "github_rls_url": "https://github.com/coqui-ai/TTS/releases/download/v0.0.9/tts_models--fr--mai--tacotron2-DDC.zip",
"default_vocoder": "vocoder_models/universal/libri-tts/fullband-melgan", "default_vocoder": "vocoder_models/universal/libri-tts/fullband-melgan",
"commit": "", "commit": "",
"author": "Eren Gölge @erogol", "author": "Eren Gölge @erogol",
"license": "MPL", "license": "MPL",
"contact":"egolge@coqui.com" "contact": "egolge@coqui.com"
} }
} }
}, },
"zh-CN":{ "zh-CN": {
"baker":{ "baker": {
"tacotron2-DDC-GST":{ "tacotron2-DDC-GST": {
"github_rls_url": "https://github.com/coqui-ai/TTS/releases/download/v0.0.10/tts_models--zh-CN--baker--tacotron2-DDC-GST.zip", "github_rls_url": "https://github.com/coqui-ai/TTS/releases/download/v0.0.10/tts_models--zh-CN--baker--tacotron2-DDC-GST.zip",
"commit": "unknown", "commit": "unknown",
"author": "@kirianguiller", "author": "@kirianguiller",
@ -107,9 +132,9 @@
} }
} }
}, },
"nl":{ "nl": {
"mai":{ "mai": {
"tacotron2-DDC":{ "tacotron2-DDC": {
"github_rls_url": "https://github.com/coqui-ai/TTS/releases/download/v0.0.10/tts_models--nl--mai--tacotron2-DDC.zip", "github_rls_url": "https://github.com/coqui-ai/TTS/releases/download/v0.0.10/tts_models--nl--mai--tacotron2-DDC.zip",
"author": "@r-dh", "author": "@r-dh",
"default_vocoder": "vocoder_models/nl/mai/parallel-wavegan", "default_vocoder": "vocoder_models/nl/mai/parallel-wavegan",
@ -118,9 +143,9 @@
} }
} }
}, },
"de":{ "de": {
"thorsten":{ "thorsten": {
"tacotron2-DCA":{ "tacotron2-DCA": {
"github_rls_url": "https://github.com/coqui-ai/TTS/releases/download/v0.0.11/tts_models--de--thorsten--tacotron2-DCA.zip", "github_rls_url": "https://github.com/coqui-ai/TTS/releases/download/v0.0.11/tts_models--de--thorsten--tacotron2-DCA.zip",
"default_vocoder": "vocoder_models/de/thorsten/fullband-melgan", "default_vocoder": "vocoder_models/de/thorsten/fullband-melgan",
"author": "@thorstenMueller", "author": "@thorstenMueller",
@ -128,9 +153,9 @@
} }
} }
}, },
"ja":{ "ja": {
"kokoro":{ "kokoro": {
"tacotron2-DDC":{ "tacotron2-DDC": {
"github_rls_url": "https://github.com/coqui-ai/TTS/releases/download/v0.0.15/tts_models--jp--kokoro--tacotron2-DDC.zip", "github_rls_url": "https://github.com/coqui-ai/TTS/releases/download/v0.0.15/tts_models--jp--kokoro--tacotron2-DDC.zip",
"default_vocoder": "vocoder_models/universal/libri-tts/wavegrad", "default_vocoder": "vocoder_models/universal/libri-tts/wavegrad",
"description": "Tacotron2 with Double Decoder Consistency trained with Kokoro Speech Dataset.", "description": "Tacotron2 with Double Decoder Consistency trained with Kokoro Speech Dataset.",
@ -140,54 +165,62 @@
} }
} }
}, },
"vocoder_models":{ "vocoder_models": {
"universal":{ "universal": {
"libri-tts":{ "libri-tts": {
"wavegrad":{ "wavegrad": {
"github_rls_url": "https://github.com/coqui-ai/TTS/releases/download/v0.0.9/vocoder_models--universal--libri-tts--wavegrad.zip", "github_rls_url": "https://github.com/coqui-ai/TTS/releases/download/v0.0.9/vocoder_models--universal--libri-tts--wavegrad.zip",
"commit": "ea976b0", "commit": "ea976b0",
"author": "Eren Gölge @erogol", "author": "Eren Gölge @erogol",
"license": "MPL", "license": "MPL",
"contact":"egolge@coqui.com" "contact": "egolge@coqui.com"
}, },
"fullband-melgan":{ "fullband-melgan": {
"github_rls_url": "https://github.com/coqui-ai/TTS/releases/download/v0.0.9/vocoder_models--universal--libri-tts--fullband-melgan.zip", "github_rls_url": "https://github.com/coqui-ai/TTS/releases/download/v0.0.9/vocoder_models--universal--libri-tts--fullband-melgan.zip",
"commit": "4132240", "commit": "4132240",
"author": "Eren Gölge @erogol", "author": "Eren Gölge @erogol",
"license": "MPL", "license": "MPL",
"contact":"egolge@coqui.com" "contact": "egolge@coqui.com"
} }
} }
}, },
"en": { "en": {
"ek1":{ "ek1": {
"wavegrad": { "wavegrad": {
"description": "EK1 en-rp wavegrad by NMStoker", "description": "EK1 en-rp wavegrad by NMStoker",
"github_rls_url": "https://github.com/coqui-ai/TTS/releases/download/v0.0.10/vocoder_models--en--ek1--wavegrad.zip", "github_rls_url": "https://github.com/coqui-ai/TTS/releases/download/v0.0.10/vocoder_models--en--ek1--wavegrad.zip",
"commit": "c802255" "commit": "c802255"
} }
}, },
"ljspeech":{ "ljspeech": {
"multiband-melgan":{ "multiband-melgan": {
"github_rls_url": "https://github.com/coqui-ai/TTS/releases/download/v0.0.9/vocoder_models--en--ljspeech--mulitband-melgan.zip", "github_rls_url": "https://github.com/coqui-ai/TTS/releases/download/v0.0.9/vocoder_models--en--ljspeech--mulitband-melgan.zip",
"commit": "ea976b0", "commit": "ea976b0",
"author": "Eren Gölge @erogol", "author": "Eren Gölge @erogol",
"license": "MPL", "license": "MPL",
"contact":"egolge@coqui.com" "contact": "egolge@coqui.com"
}, },
"hifigan_v2":{ "hifigan_v2": {
"description": "HiFiGAN_v2 LJSpeech vocoder from https://arxiv.org/abs/2010.05646.", "description": "HiFiGAN_v2 LJSpeech vocoder from https://arxiv.org/abs/2010.05646.",
"github_rls_url": "https://github.com/coqui-ai/TTS/releases/download/v0.0.12/vocoder_model--en--ljspeech-hifigan_v2.zip", "github_rls_url": "https://github.com/coqui-ai/TTS/releases/download/v0.0.12/vocoder_model--en--ljspeech-hifigan_v2.zip",
"commit": "bae2ad0f", "commit": "bae2ad0f",
"author": "@erogol", "author": "@erogol",
"license": "", "license": "",
"contact": "egolge@coqui.ai" "contact": "egolge@coqui.ai"
},
"univnet": {
"description": "UnivNet model trained on LJSpeech to complement the TacotronDDC_ph model.",
"github_rls_url": "https://github.com/coqui-ai/TTS/releases/download/v0.2.0/vocoder_models--en--ljspeech--univnet.zip",
"commit": "3900448",
"author": "Eren @erogol",
"license": "",
"contact": "egolge@coqui.ai"
} }
}, },
"vctk":{ "vctk": {
"hifigan_v2":{ "hifigan_v2": {
"description": "Finetuned and intended to be used with tts_models/en/vctk/sc-glow-tts", "description": "Finetuned and intended to be used with tts_models/en/vctk/sc-glow-tts",
"github_rls_url":"https://github.com/coqui-ai/TTS/releases/download/v0.0.12/vocoder_model--en--vctk--hifigan_v2.zip", "github_rls_url": "https://github.com/coqui-ai/TTS/releases/download/v0.0.12/vocoder_model--en--vctk--hifigan_v2.zip",
"commit": "2f07160", "commit": "2f07160",
"author": "Edresson Casanova", "author": "Edresson Casanova",
"license": "", "license": "",
@ -195,9 +228,9 @@
} }
}, },
"sam": { "sam": {
"hifigan_v2":{ "hifigan_v2": {
"description": "Finetuned and intended to be used with tts_models/en/sam/tacotron_DDC", "description": "Finetuned and intended to be used with tts_models/en/sam/tacotron_DDC",
"github_rls_url":"https://github.com/coqui-ai/TTS/releases/download/v0.0.13/vocoder_models--en--sam--hifigan_v2.zip", "github_rls_url": "https://github.com/coqui-ai/TTS/releases/download/v0.0.13/vocoder_models--en--sam--hifigan_v2.zip",
"commit": "2f07160", "commit": "2f07160",
"author": "Eren Gölge @erogol", "author": "Eren Gölge @erogol",
"license": "", "license": "",
@ -205,28 +238,38 @@
} }
} }
}, },
"nl":{ "nl": {
"mai":{ "mai": {
"parallel-wavegan":{ "parallel-wavegan": {
"github_rls_url": "https://github.com/coqui-ai/TTS/releases/download/v0.0.10/vocoder_models--nl--mai--parallel-wavegan.zip", "github_rls_url": "https://github.com/coqui-ai/TTS/releases/download/v0.0.10/vocoder_models--nl--mai--parallel-wavegan.zip",
"author": "@r-dh", "author": "@r-dh",
"commit": "unknown" "commit": "unknown"
} }
} }
}, },
"de":{ "de": {
"thorsten":{ "thorsten": {
"wavegrad":{ "wavegrad": {
"github_rls_url": "https://github.com/coqui-ai/TTS/releases/download/v0.0.11/vocoder_models--de--thorsten--wavegrad.zip", "github_rls_url": "https://github.com/coqui-ai/TTS/releases/download/v0.0.11/vocoder_models--de--thorsten--wavegrad.zip",
"author": "@thorstenMueller", "author": "@thorstenMueller",
"commit": "unknown" "commit": "unknown"
}, },
"fullband-melgan":{ "fullband-melgan": {
"github_rls_url": "https://github.com/coqui-ai/TTS/releases/download/v0.1.3/vocoder_models--de--thorsten--fullband-melgan.zip", "github_rls_url": "https://github.com/coqui-ai/TTS/releases/download/v0.1.3/vocoder_models--de--thorsten--fullband-melgan.zip",
"author": "@thorstenMueller", "author": "@thorstenMueller",
"commit": "unknown" "commit": "unknown"
} }
} }
},
"ja": {
"kokoro": {
"hifigan_v1": {
"github_rls_url": "https://github.com/coqui-ai/TTS/releases/download/v0.2.0/vocoder_models--ja--kokoro--hifigan_v1.zip",
"description": "HifiGAN model trained for kokoro dataset by @kaiidams",
"author": "@kaiidams",
"commit": "3900448"
}
}
} }
} }
} }