939 lines
43 KiB
JSON
939 lines
43 KiB
JSON
{
|
|
"tts_models": {
|
|
"multilingual": {
|
|
"multi-dataset": {
|
|
"xtts_v2": {
|
|
"description": "XTTS-v2.0.3 by Coqui with 17 languages.",
|
|
"hf_url": [
|
|
"https://coqui.gateway.scarf.sh/hf-coqui/XTTS-v2/main/model.pth",
|
|
"https://coqui.gateway.scarf.sh/hf-coqui/XTTS-v2/main/config.json",
|
|
"https://coqui.gateway.scarf.sh/hf-coqui/XTTS-v2/main/vocab.json",
|
|
"https://coqui.gateway.scarf.sh/hf-coqui/XTTS-v2/main/hash.md5",
|
|
"https://coqui.gateway.scarf.sh/hf-coqui/XTTS-v2/main/speakers_xtts.pth"
|
|
],
|
|
"model_hash": "10f92b55c512af7a8d39d650547a15a7",
|
|
"default_vocoder": null,
|
|
"commit": "480a6cdf7",
|
|
"license": "CPML",
|
|
"contact": "info@coqui.ai",
|
|
"tos_required": true
|
|
},
|
|
"xtts_v1.1": {
|
|
"description": "XTTS-v1.1 by Coqui with 14 languages, cross-language voice cloning and reference leak fixed.",
|
|
"hf_url": [
|
|
"https://coqui.gateway.scarf.sh/hf-coqui/XTTS-v1/v1.1.2/model.pth",
|
|
"https://coqui.gateway.scarf.sh/hf-coqui/XTTS-v1/v1.1.2/config.json",
|
|
"https://coqui.gateway.scarf.sh/hf-coqui/XTTS-v1/v1.1.2/vocab.json",
|
|
"https://coqui.gateway.scarf.sh/hf-coqui/XTTS-v1/v1.1.2/hash.md5"
|
|
],
|
|
"model_hash": "7c62beaf58d39b729de287330dc254e7b515677416839b649a50e7cf74c3df59",
|
|
"default_vocoder": null,
|
|
"commit": "82910a63",
|
|
"license": "CPML",
|
|
"contact": "info@coqui.ai",
|
|
"tos_required": true
|
|
},
|
|
"your_tts": {
|
|
"description": "Your TTS model accompanying the paper https://arxiv.org/abs/2112.02418",
|
|
"github_rls_url": "https://coqui.gateway.scarf.sh/v0.10.1_models/tts_models--multilingual--multi-dataset--your_tts.zip",
|
|
"default_vocoder": null,
|
|
"commit": "e9a1953e",
|
|
"license": "CC BY-NC-ND 4.0",
|
|
"contact": "egolge@coqui.ai"
|
|
},
|
|
"bark": {
|
|
"description": "🐶 Bark TTS model released by suno-ai. You can find the original implementation in https://github.com/suno-ai/bark.",
|
|
"hf_url": [
|
|
"https://coqui.gateway.scarf.sh/hf/bark/coarse_2.pt",
|
|
"https://coqui.gateway.scarf.sh/hf/bark/fine_2.pt",
|
|
"https://coqui.gateway.scarf.sh/hf/text_2.pt",
|
|
"https://coqui.gateway.scarf.sh/hf/bark/config.json",
|
|
"https://coqui.gateway.scarf.sh/hf/bark/hubert.pt",
|
|
"https://coqui.gateway.scarf.sh/hf/bark/tokenizer.pth"
|
|
],
|
|
"default_vocoder": null,
|
|
"commit": "e9a1953e",
|
|
"license": "MIT",
|
|
"contact": "https://www.suno.ai/"
|
|
}
|
|
}
|
|
},
|
|
"bg": {
|
|
"cv": {
|
|
"vits": {
|
|
"github_rls_url": "https://coqui.gateway.scarf.sh/v0.8.0_models/tts_models--bg--cv--vits.zip",
|
|
"default_vocoder": null,
|
|
"commit": null,
|
|
"author": "@NeonGeckoCom",
|
|
"license": "bsd-3-clause"
|
|
}
|
|
}
|
|
},
|
|
"cs": {
|
|
"cv": {
|
|
"vits": {
|
|
"github_rls_url": "https://coqui.gateway.scarf.sh/v0.8.0_models/tts_models--cs--cv--vits.zip",
|
|
"default_vocoder": null,
|
|
"commit": null,
|
|
"author": "@NeonGeckoCom",
|
|
"license": "bsd-3-clause"
|
|
}
|
|
}
|
|
},
|
|
"da": {
|
|
"cv": {
|
|
"vits": {
|
|
"github_rls_url": "https://coqui.gateway.scarf.sh/v0.8.0_models/tts_models--da--cv--vits.zip",
|
|
"default_vocoder": null,
|
|
"commit": null,
|
|
"author": "@NeonGeckoCom",
|
|
"license": "bsd-3-clause"
|
|
}
|
|
}
|
|
},
|
|
"et": {
|
|
"cv": {
|
|
"vits": {
|
|
"github_rls_url": "https://coqui.gateway.scarf.sh/v0.8.0_models/tts_models--et--cv--vits.zip",
|
|
"default_vocoder": null,
|
|
"commit": null,
|
|
"author": "@NeonGeckoCom",
|
|
"license": "bsd-3-clause"
|
|
}
|
|
}
|
|
},
|
|
"ga": {
|
|
"cv": {
|
|
"vits": {
|
|
"github_rls_url": "https://coqui.gateway.scarf.sh/v0.8.0_models/tts_models--ga--cv--vits.zip",
|
|
"default_vocoder": null,
|
|
"commit": null,
|
|
"author": "@NeonGeckoCom",
|
|
"license": "bsd-3-clause"
|
|
}
|
|
}
|
|
},
|
|
"en": {
|
|
"ek1": {
|
|
"tacotron2": {
|
|
"description": "EK1 en-rp tacotron2 by NMStoker",
|
|
"github_rls_url": "https://coqui.gateway.scarf.sh/v0.6.1_models/tts_models--en--ek1--tacotron2.zip",
|
|
"default_vocoder": "vocoder_models/en/ek1/wavegrad",
|
|
"commit": "c802255",
|
|
"license": "apache 2.0"
|
|
}
|
|
},
|
|
"ljspeech": {
|
|
"tacotron2-DDC": {
|
|
"description": "Tacotron2 with Double Decoder Consistency.",
|
|
"github_rls_url": "https://coqui.gateway.scarf.sh/v0.6.1_models/tts_models--en--ljspeech--tacotron2-DDC.zip",
|
|
"default_vocoder": "vocoder_models/en/ljspeech/hifigan_v2",
|
|
"commit": "bae2ad0f",
|
|
"author": "Eren Gölge @erogol",
|
|
"license": "apache 2.0",
|
|
"contact": "egolge@coqui.com"
|
|
},
|
|
"tacotron2-DDC_ph": {
|
|
"description": "Tacotron2 with Double Decoder Consistency with phonemes.",
|
|
"github_rls_url": "https://coqui.gateway.scarf.sh/v0.6.1_models/tts_models--en--ljspeech--tacotron2-DDC_ph.zip",
|
|
"default_vocoder": "vocoder_models/en/ljspeech/univnet",
|
|
"commit": "3900448",
|
|
"author": "Eren Gölge @erogol",
|
|
"license": "apache 2.0",
|
|
"contact": "egolge@coqui.com"
|
|
},
|
|
"glow-tts": {
|
|
"description": "",
|
|
"github_rls_url": "https://coqui.gateway.scarf.sh/v0.6.1_models/tts_models--en--ljspeech--glow-tts.zip",
|
|
"stats_file": null,
|
|
"default_vocoder": "vocoder_models/en/ljspeech/multiband-melgan",
|
|
"commit": "",
|
|
"author": "Eren Gölge @erogol",
|
|
"license": "MPL",
|
|
"contact": "egolge@coqui.com"
|
|
},
|
|
"speedy-speech": {
|
|
"description": "Speedy Speech model trained on LJSpeech dataset using the Alignment Network for learning the durations.",
|
|
"github_rls_url": "https://coqui.gateway.scarf.sh/v0.6.1_models/tts_models--en--ljspeech--speedy-speech.zip",
|
|
"stats_file": null,
|
|
"default_vocoder": "vocoder_models/en/ljspeech/hifigan_v2",
|
|
"commit": "4581e3d",
|
|
"author": "Eren Gölge @erogol",
|
|
"license": "apache 2.0",
|
|
"contact": "egolge@coqui.com"
|
|
},
|
|
"tacotron2-DCA": {
|
|
"description": "",
|
|
"github_rls_url": "https://coqui.gateway.scarf.sh/v0.6.1_models/tts_models--en--ljspeech--tacotron2-DCA.zip",
|
|
"default_vocoder": "vocoder_models/en/ljspeech/multiband-melgan",
|
|
"commit": "",
|
|
"author": "Eren Gölge @erogol",
|
|
"license": "MPL",
|
|
"contact": "egolge@coqui.com"
|
|
},
|
|
"vits": {
|
|
"description": "VITS is an End2End TTS model trained on LJSpeech dataset with phonemes.",
|
|
"github_rls_url": "https://coqui.gateway.scarf.sh/v0.6.1_models/tts_models--en--ljspeech--vits.zip",
|
|
"default_vocoder": null,
|
|
"commit": "3900448",
|
|
"author": "Eren Gölge @erogol",
|
|
"license": "apache 2.0",
|
|
"contact": "egolge@coqui.com"
|
|
},
|
|
"vits--neon": {
|
|
"github_rls_url": "https://coqui.gateway.scarf.sh/v0.8.0_models/tts_models--en--ljspeech--vits.zip",
|
|
"default_vocoder": null,
|
|
"author": "@NeonGeckoCom",
|
|
"license": "bsd-3-clause",
|
|
"contact": null,
|
|
"commit": null
|
|
},
|
|
"fast_pitch": {
|
|
"description": "FastPitch model trained on LJSpeech using the Aligner Network",
|
|
"github_rls_url": "https://coqui.gateway.scarf.sh/v0.6.1_models/tts_models--en--ljspeech--fast_pitch.zip",
|
|
"default_vocoder": "vocoder_models/en/ljspeech/hifigan_v2",
|
|
"commit": "b27b3ba",
|
|
"author": "Eren Gölge @erogol",
|
|
"license": "apache 2.0",
|
|
"contact": "egolge@coqui.com"
|
|
},
|
|
"overflow": {
|
|
"description": "Overflow model trained on LJSpeech",
|
|
"github_rls_url": "https://coqui.gateway.scarf.sh/v0.10.0_models/tts_models--en--ljspeech--overflow.zip",
|
|
"default_vocoder": "vocoder_models/en/ljspeech/hifigan_v2",
|
|
"commit": "3b1a28f",
|
|
"author": "Eren Gölge @erogol",
|
|
"license": "apache 2.0",
|
|
"contact": "egolge@coqui.ai"
|
|
},
|
|
"neural_hmm": {
|
|
"description": "Neural HMM model trained on LJSpeech",
|
|
"github_rls_url": "https://coqui.gateway.scarf.sh/v0.11.0_models/tts_models--en--ljspeech--neural_hmm.zip",
|
|
"default_vocoder": "vocoder_models/en/ljspeech/hifigan_v2",
|
|
"commit": "3b1a28f",
|
|
"author": "Shivam Metha @shivammehta25",
|
|
"license": "apache 2.0",
|
|
"contact": "d83ee8fe45e3c0d776d4a865aca21d7c2ac324c4"
|
|
}
|
|
},
|
|
"vctk": {
|
|
"vits": {
|
|
"description": "VITS End2End TTS model trained on VCTK dataset with 109 different speakers with EN accent.",
|
|
"github_rls_url": "https://coqui.gateway.scarf.sh/v0.6.1_models/tts_models--en--vctk--vits.zip",
|
|
"default_vocoder": null,
|
|
"commit": "3900448",
|
|
"author": "Eren @erogol",
|
|
"license": "apache 2.0",
|
|
"contact": "egolge@coqui.ai"
|
|
},
|
|
"fast_pitch": {
|
|
"description": "FastPitch model trained on VCTK dataseset.",
|
|
"github_rls_url": "https://coqui.gateway.scarf.sh/v0.6.1_models/tts_models--en--vctk--fast_pitch.zip",
|
|
"default_vocoder": null,
|
|
"commit": "bdab788d",
|
|
"author": "Eren @erogol",
|
|
"license": "CC BY-NC-ND 4.0",
|
|
"contact": "egolge@coqui.ai"
|
|
}
|
|
},
|
|
"sam": {
|
|
"tacotron-DDC": {
|
|
"description": "Tacotron2 with Double Decoder Consistency trained with Aceenture's Sam dataset.",
|
|
"github_rls_url": "https://coqui.gateway.scarf.sh/v0.6.1_models/tts_models--en--sam--tacotron-DDC.zip",
|
|
"default_vocoder": "vocoder_models/en/sam/hifigan_v2",
|
|
"commit": "bae2ad0f",
|
|
"author": "Eren Gölge @erogol",
|
|
"license": "apache 2.0",
|
|
"contact": "egolge@coqui.com"
|
|
}
|
|
},
|
|
"blizzard2013": {
|
|
"capacitron-t2-c50": {
|
|
"description": "Capacitron additions to Tacotron 2 with Capacity at 50 as in https://arxiv.org/pdf/1906.03402.pdf",
|
|
"github_rls_url": "https://coqui.gateway.scarf.sh/v0.7.0_models/tts_models--en--blizzard2013--capacitron-t2-c50.zip",
|
|
"commit": "d6284e7",
|
|
"default_vocoder": "vocoder_models/en/blizzard2013/hifigan_v2",
|
|
"author": "Adam Froghyar @a-froghyar",
|
|
"license": "apache 2.0",
|
|
"contact": "adamfroghyar@gmail.com"
|
|
},
|
|
"capacitron-t2-c150_v2": {
|
|
"description": "Capacitron additions to Tacotron 2 with Capacity at 150 as in https://arxiv.org/pdf/1906.03402.pdf",
|
|
"github_rls_url": "https://coqui.gateway.scarf.sh/v0.7.1_models/tts_models--en--blizzard2013--capacitron-t2-c150_v2.zip",
|
|
"commit": "a67039d",
|
|
"default_vocoder": "vocoder_models/en/blizzard2013/hifigan_v2",
|
|
"author": "Adam Froghyar @a-froghyar",
|
|
"license": "apache 2.0",
|
|
"contact": "adamfroghyar@gmail.com"
|
|
}
|
|
},
|
|
"multi-dataset": {
|
|
"tortoise-v2": {
|
|
"description": "Tortoise tts model https://github.com/neonbjb/tortoise-tts",
|
|
"github_rls_url": [
|
|
"https://coqui.gateway.scarf.sh/v0.14.1_models/autoregressive.pth",
|
|
"https://coqui.gateway.scarf.sh/v0.14.1_models/clvp2.pth",
|
|
"https://coqui.gateway.scarf.sh/v0.14.1_models/cvvp.pth",
|
|
"https://coqui.gateway.scarf.sh/v0.14.1_models/diffusion_decoder.pth",
|
|
"https://coqui.gateway.scarf.sh/v0.14.1_models/rlg_auto.pth",
|
|
"https://coqui.gateway.scarf.sh/v0.14.1_models/rlg_diffuser.pth",
|
|
"https://coqui.gateway.scarf.sh/v0.14.1_models/vocoder.pth",
|
|
"https://coqui.gateway.scarf.sh/v0.14.1_models/mel_norms.pth",
|
|
"https://coqui.gateway.scarf.sh/v0.14.1_models/config.json"
|
|
],
|
|
"commit": "c1875f6",
|
|
"default_vocoder": null,
|
|
"author": "@neonbjb - James Betker, @manmay-nakhashi Manmay Nakhashi",
|
|
"license": "apache 2.0"
|
|
}
|
|
},
|
|
"jenny": {
|
|
"jenny": {
|
|
"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",
|
|
"github_rls_url": "https://coqui.gateway.scarf.sh/v0.14.0_models/tts_models--en--jenny--jenny.zip",
|
|
"default_vocoder": null,
|
|
"commit": "ba40a1c",
|
|
"license": "custom - see https://github.com/dioco-group/jenny-tts-dataset#important",
|
|
"author": "@noml4u"
|
|
}
|
|
}
|
|
},
|
|
"es": {
|
|
"mai": {
|
|
"tacotron2-DDC": {
|
|
"github_rls_url": "https://coqui.gateway.scarf.sh/v0.6.1_models/tts_models--es--mai--tacotron2-DDC.zip",
|
|
"default_vocoder": "vocoder_models/universal/libri-tts/fullband-melgan",
|
|
"commit": "",
|
|
"author": "Eren Gölge @erogol",
|
|
"license": "MPL",
|
|
"contact": "egolge@coqui.com"
|
|
}
|
|
},
|
|
"css10": {
|
|
"vits": {
|
|
"github_rls_url": "https://coqui.gateway.scarf.sh/v0.8.0_models/tts_models--es--css10--vits.zip",
|
|
"default_vocoder": null,
|
|
"commit": null,
|
|
"author": "@NeonGeckoCom",
|
|
"license": "bsd-3-clause"
|
|
}
|
|
}
|
|
},
|
|
"fr": {
|
|
"mai": {
|
|
"tacotron2-DDC": {
|
|
"github_rls_url": "https://coqui.gateway.scarf.sh/v0.6.1_models/tts_models--fr--mai--tacotron2-DDC.zip",
|
|
"default_vocoder": "vocoder_models/universal/libri-tts/fullband-melgan",
|
|
"commit": null,
|
|
"author": "Eren Gölge @erogol",
|
|
"license": "MPL",
|
|
"contact": "egolge@coqui.com"
|
|
}
|
|
},
|
|
"css10": {
|
|
"vits": {
|
|
"github_rls_url": "https://coqui.gateway.scarf.sh/v0.8.0_models/tts_models--fr--css10--vits.zip",
|
|
"default_vocoder": null,
|
|
"commit": null,
|
|
"author": "@NeonGeckoCom",
|
|
"license": "bsd-3-clause"
|
|
}
|
|
}
|
|
},
|
|
"uk": {
|
|
"mai": {
|
|
"glow-tts": {
|
|
"github_rls_url": "https://coqui.gateway.scarf.sh/v0.6.1_models/tts_models--uk--mai--glow-tts.zip",
|
|
"author": "@robinhad",
|
|
"commit": "bdab788d",
|
|
"license": "MIT",
|
|
"contact": "",
|
|
"default_vocoder": "vocoder_models/uk/mai/multiband-melgan"
|
|
},
|
|
"vits": {
|
|
"github_rls_url": "https://coqui.gateway.scarf.sh/v0.8.0_models/tts_models--uk--mai--vits.zip",
|
|
"default_vocoder": null,
|
|
"commit": null,
|
|
"author": "@NeonGeckoCom",
|
|
"license": "bsd-3-clause"
|
|
}
|
|
}
|
|
},
|
|
"zh-CN": {
|
|
"baker": {
|
|
"tacotron2-DDC-GST": {
|
|
"github_rls_url": "https://coqui.gateway.scarf.sh/v0.6.1_models/tts_models--zh-CN--baker--tacotron2-DDC-GST.zip",
|
|
"commit": "unknown",
|
|
"author": "@kirianguiller",
|
|
"license": "apache 2.0",
|
|
"default_vocoder": null
|
|
}
|
|
}
|
|
},
|
|
"nl": {
|
|
"mai": {
|
|
"tacotron2-DDC": {
|
|
"github_rls_url": "https://coqui.gateway.scarf.sh/v0.6.1_models/tts_models--nl--mai--tacotron2-DDC.zip",
|
|
"author": "@r-dh",
|
|
"license": "apache 2.0",
|
|
"default_vocoder": "vocoder_models/nl/mai/parallel-wavegan",
|
|
"stats_file": null,
|
|
"commit": "540d811"
|
|
}
|
|
},
|
|
"css10": {
|
|
"vits": {
|
|
"github_rls_url": "https://coqui.gateway.scarf.sh/v0.8.0_models/tts_models--nl--css10--vits.zip",
|
|
"default_vocoder": null,
|
|
"commit": null,
|
|
"author": "@NeonGeckoCom",
|
|
"license": "bsd-3-clause"
|
|
}
|
|
}
|
|
},
|
|
"de": {
|
|
"thorsten": {
|
|
"tacotron2-DCA": {
|
|
"github_rls_url": "https://coqui.gateway.scarf.sh/v0.6.1_models/tts_models--de--thorsten--tacotron2-DCA.zip",
|
|
"default_vocoder": "vocoder_models/de/thorsten/fullband-melgan",
|
|
"author": "@thorstenMueller",
|
|
"license": "apache 2.0",
|
|
"commit": "unknown"
|
|
},
|
|
"vits": {
|
|
"github_rls_url": "https://coqui.gateway.scarf.sh/v0.7.0_models/tts_models--de--thorsten--vits.zip",
|
|
"default_vocoder": null,
|
|
"author": "@thorstenMueller",
|
|
"license": "apache 2.0",
|
|
"commit": "unknown"
|
|
},
|
|
"tacotron2-DDC": {
|
|
"github_rls_url": "https://coqui.gateway.scarf.sh/v0.8.0_models/tts_models--de--thorsten--tacotron2-DDC.zip",
|
|
"default_vocoder": "vocoder_models/de/thorsten/hifigan_v1",
|
|
"description": "Thorsten-Dec2021-22k-DDC",
|
|
"author": "@thorstenMueller",
|
|
"license": "apache 2.0",
|
|
"commit": "unknown"
|
|
}
|
|
},
|
|
"css10": {
|
|
"vits-neon": {
|
|
"github_rls_url": "https://coqui.gateway.scarf.sh/v0.8.0_models/tts_models--de--css10--vits.zip",
|
|
"default_vocoder": null,
|
|
"author": "@NeonGeckoCom",
|
|
"license": "bsd-3-clause",
|
|
"commit": null
|
|
}
|
|
}
|
|
},
|
|
"ja": {
|
|
"kokoro": {
|
|
"tacotron2-DDC": {
|
|
"github_rls_url": "https://coqui.gateway.scarf.sh/v0.6.1_models/tts_models--ja--kokoro--tacotron2-DDC.zip",
|
|
"default_vocoder": "vocoder_models/ja/kokoro/hifigan_v1",
|
|
"description": "Tacotron2 with Double Decoder Consistency trained with Kokoro Speech Dataset.",
|
|
"author": "@kaiidams",
|
|
"license": "apache 2.0",
|
|
"commit": "401fbd89"
|
|
}
|
|
}
|
|
},
|
|
"tr": {
|
|
"common-voice": {
|
|
"glow-tts": {
|
|
"github_rls_url": "https://coqui.gateway.scarf.sh/v0.6.1_models/tts_models--tr--common-voice--glow-tts.zip",
|
|
"default_vocoder": "vocoder_models/tr/common-voice/hifigan",
|
|
"license": "MIT",
|
|
"description": "Turkish GlowTTS model using an unknown speaker from the Common-Voice dataset.",
|
|
"author": "Fatih Akademi",
|
|
"commit": null
|
|
}
|
|
}
|
|
},
|
|
"it": {
|
|
"mai_female": {
|
|
"glow-tts": {
|
|
"github_rls_url": "https://coqui.gateway.scarf.sh/v0.6.1_models/tts_models--it--mai_female--glow-tts.zip",
|
|
"default_vocoder": null,
|
|
"description": "GlowTTS model as explained on https://github.com/coqui-ai/TTS/issues/1148.",
|
|
"author": "@nicolalandro",
|
|
"license": "apache 2.0",
|
|
"commit": null
|
|
},
|
|
"vits": {
|
|
"github_rls_url": "https://coqui.gateway.scarf.sh/v0.6.1_models/tts_models--it--mai_female--vits.zip",
|
|
"default_vocoder": null,
|
|
"description": "GlowTTS model as explained on https://github.com/coqui-ai/TTS/issues/1148.",
|
|
"author": "@nicolalandro",
|
|
"license": "apache 2.0",
|
|
"commit": null
|
|
}
|
|
},
|
|
"mai_male": {
|
|
"glow-tts": {
|
|
"github_rls_url": "https://coqui.gateway.scarf.sh/v0.6.1_models/tts_models--it--mai_male--glow-tts.zip",
|
|
"default_vocoder": null,
|
|
"description": "GlowTTS model as explained on https://github.com/coqui-ai/TTS/issues/1148.",
|
|
"author": "@nicolalandro",
|
|
"license": "apache 2.0",
|
|
"commit": null
|
|
},
|
|
"vits": {
|
|
"github_rls_url": "https://coqui.gateway.scarf.sh/v0.6.1_models/tts_models--it--mai_male--vits.zip",
|
|
"default_vocoder": null,
|
|
"description": "GlowTTS model as explained on https://github.com/coqui-ai/TTS/issues/1148.",
|
|
"author": "@nicolalandro",
|
|
"license": "apache 2.0",
|
|
"commit": null
|
|
}
|
|
}
|
|
},
|
|
"ewe": {
|
|
"openbible": {
|
|
"vits": {
|
|
"github_rls_url": "https://coqui.gateway.scarf.sh/v0.6.2_models/tts_models--ewe--openbible--vits.zip",
|
|
"default_vocoder": null,
|
|
"license": "CC-BY-SA 4.0",
|
|
"description": "Original work (audio and text) by Biblica available for free at www.biblica.com and open.bible.",
|
|
"author": "@coqui_ai",
|
|
"commit": "1b22f03"
|
|
}
|
|
}
|
|
},
|
|
"hau": {
|
|
"openbible": {
|
|
"vits": {
|
|
"github_rls_url": "https://coqui.gateway.scarf.sh/v0.6.2_models/tts_models--hau--openbible--vits.zip",
|
|
"default_vocoder": null,
|
|
"license": "CC-BY-SA 4.0",
|
|
"description": "Original work (audio and text) by Biblica available for free at www.biblica.com and open.bible.",
|
|
"author": "@coqui_ai",
|
|
"commit": "1b22f03"
|
|
}
|
|
}
|
|
},
|
|
"lin": {
|
|
"openbible": {
|
|
"vits": {
|
|
"github_rls_url": "https://coqui.gateway.scarf.sh/v0.6.2_models/tts_models--lin--openbible--vits.zip",
|
|
"default_vocoder": null,
|
|
"license": "CC-BY-SA 4.0",
|
|
"description": "Original work (audio and text) by Biblica available for free at www.biblica.com and open.bible.",
|
|
"author": "@coqui_ai",
|
|
"commit": "1b22f03"
|
|
}
|
|
}
|
|
},
|
|
"tw_akuapem": {
|
|
"openbible": {
|
|
"vits": {
|
|
"github_rls_url": "https://coqui.gateway.scarf.sh/v0.6.2_models/tts_models--tw_akuapem--openbible--vits.zip",
|
|
"default_vocoder": null,
|
|
"license": "CC-BY-SA 4.0",
|
|
"description": "Original work (audio and text) by Biblica available for free at www.biblica.com and open.bible.",
|
|
"author": "@coqui_ai",
|
|
"commit": "1b22f03"
|
|
}
|
|
}
|
|
},
|
|
"tw_asante": {
|
|
"openbible": {
|
|
"vits": {
|
|
"github_rls_url": "https://coqui.gateway.scarf.sh/v0.6.2_models/tts_models--tw_asante--openbible--vits.zip",
|
|
"default_vocoder": null,
|
|
"license": "CC-BY-SA 4.0",
|
|
"description": "Original work (audio and text) by Biblica available for free at www.biblica.com and open.bible.",
|
|
"author": "@coqui_ai",
|
|
"commit": "1b22f03"
|
|
}
|
|
}
|
|
},
|
|
"yor": {
|
|
"openbible": {
|
|
"vits": {
|
|
"github_rls_url": "https://coqui.gateway.scarf.sh/v0.6.2_models/tts_models--yor--openbible--vits.zip",
|
|
"default_vocoder": null,
|
|
"license": "CC-BY-SA 4.0",
|
|
"description": "Original work (audio and text) by Biblica available for free at www.biblica.com and open.bible.",
|
|
"author": "@coqui_ai",
|
|
"commit": "1b22f03"
|
|
}
|
|
}
|
|
},
|
|
"hu": {
|
|
"css10": {
|
|
"vits": {
|
|
"github_rls_url": "https://coqui.gateway.scarf.sh/v0.8.0_models/tts_models--hu--css10--vits.zip",
|
|
"default_vocoder": null,
|
|
"commit": null,
|
|
"author": "@NeonGeckoCom",
|
|
"license": "bsd-3-clause"
|
|
}
|
|
}
|
|
},
|
|
"el": {
|
|
"cv": {
|
|
"vits": {
|
|
"github_rls_url": "https://coqui.gateway.scarf.sh/v0.8.0_models/tts_models--el--cv--vits.zip",
|
|
"default_vocoder": null,
|
|
"commit": null,
|
|
"author": "@NeonGeckoCom",
|
|
"license": "bsd-3-clause"
|
|
}
|
|
}
|
|
},
|
|
"fi": {
|
|
"css10": {
|
|
"vits": {
|
|
"github_rls_url": "https://coqui.gateway.scarf.sh/v0.8.0_models/tts_models--fi--css10--vits.zip",
|
|
"default_vocoder": null,
|
|
"commit": null,
|
|
"author": "@NeonGeckoCom",
|
|
"license": "bsd-3-clause"
|
|
}
|
|
}
|
|
},
|
|
"hr": {
|
|
"cv": {
|
|
"vits": {
|
|
"github_rls_url": "https://coqui.gateway.scarf.sh/v0.8.0_models/tts_models--hr--cv--vits.zip",
|
|
"default_vocoder": null,
|
|
"commit": null,
|
|
"author": "@NeonGeckoCom",
|
|
"license": "bsd-3-clause"
|
|
}
|
|
}
|
|
},
|
|
"lt": {
|
|
"cv": {
|
|
"vits": {
|
|
"github_rls_url": "https://coqui.gateway.scarf.sh/v0.8.0_models/tts_models--lt--cv--vits.zip",
|
|
"default_vocoder": null,
|
|
"commit": null,
|
|
"author": "@NeonGeckoCom",
|
|
"license": "bsd-3-clause"
|
|
}
|
|
}
|
|
},
|
|
"lv": {
|
|
"cv": {
|
|
"vits": {
|
|
"github_rls_url": "https://coqui.gateway.scarf.sh/v0.8.0_models/tts_models--lv--cv--vits.zip",
|
|
"default_vocoder": null,
|
|
"commit": null,
|
|
"author": "@NeonGeckoCom",
|
|
"license": "bsd-3-clause"
|
|
}
|
|
}
|
|
},
|
|
"mt": {
|
|
"cv": {
|
|
"vits": {
|
|
"github_rls_url": "https://coqui.gateway.scarf.sh/v0.8.0_models/tts_models--mt--cv--vits.zip",
|
|
"default_vocoder": null,
|
|
"commit": null,
|
|
"author": "@NeonGeckoCom",
|
|
"license": "bsd-3-clause"
|
|
}
|
|
}
|
|
},
|
|
"pl": {
|
|
"mai_female": {
|
|
"vits": {
|
|
"github_rls_url": "https://coqui.gateway.scarf.sh/v0.8.0_models/tts_models--pl--mai_female--vits.zip",
|
|
"default_vocoder": null,
|
|
"commit": null,
|
|
"author": "@NeonGeckoCom",
|
|
"license": "bsd-3-clause"
|
|
}
|
|
}
|
|
},
|
|
"pt": {
|
|
"cv": {
|
|
"vits": {
|
|
"github_rls_url": "https://coqui.gateway.scarf.sh/v0.8.0_models/tts_models--pt--cv--vits.zip",
|
|
"default_vocoder": null,
|
|
"commit": null,
|
|
"author": "@NeonGeckoCom",
|
|
"license": "bsd-3-clause"
|
|
}
|
|
}
|
|
},
|
|
"ro": {
|
|
"cv": {
|
|
"vits": {
|
|
"github_rls_url": "https://coqui.gateway.scarf.sh/v0.8.0_models/tts_models--ro--cv--vits.zip",
|
|
"default_vocoder": null,
|
|
"commit": null,
|
|
"author": "@NeonGeckoCom",
|
|
"license": "bsd-3-clause"
|
|
}
|
|
}
|
|
},
|
|
"sk": {
|
|
"cv": {
|
|
"vits": {
|
|
"github_rls_url": "https://coqui.gateway.scarf.sh/v0.8.0_models/tts_models--sk--cv--vits.zip",
|
|
"default_vocoder": null,
|
|
"commit": null,
|
|
"author": "@NeonGeckoCom",
|
|
"license": "bsd-3-clause"
|
|
}
|
|
}
|
|
},
|
|
"sl": {
|
|
"cv": {
|
|
"vits": {
|
|
"github_rls_url": "https://coqui.gateway.scarf.sh/v0.8.0_models/tts_models--sl--cv--vits.zip",
|
|
"default_vocoder": null,
|
|
"commit": null,
|
|
"author": "@NeonGeckoCom",
|
|
"license": "bsd-3-clause"
|
|
}
|
|
}
|
|
},
|
|
"sv": {
|
|
"cv": {
|
|
"vits": {
|
|
"github_rls_url": "https://coqui.gateway.scarf.sh/v0.8.0_models/tts_models--sv--cv--vits.zip",
|
|
"default_vocoder": null,
|
|
"commit": null,
|
|
"author": "@NeonGeckoCom",
|
|
"license": "bsd-3-clause"
|
|
}
|
|
}
|
|
},
|
|
"ca": {
|
|
"custom": {
|
|
"vits": {
|
|
"github_rls_url": "https://coqui.gateway.scarf.sh/v0.10.1_models/tts_models--ca--custom--vits.zip",
|
|
"default_vocoder": null,
|
|
"commit": null,
|
|
"description": " It is trained from zero with 101460 utterances consisting of 257 speakers, approx 138 hours of speech. We used three datasets;\nFestcat and Google Catalan TTS (both TTS datasets) and also a part of Common Voice 8. It is trained with TTS v0.8.0.\nhttps://github.com/coqui-ai/TTS/discussions/930#discussioncomment-4466345",
|
|
"author": "@gullabi",
|
|
"license": "CC-BY-4.0"
|
|
}
|
|
}
|
|
},
|
|
"fa": {
|
|
"custom": {
|
|
"glow-tts": {
|
|
"github_rls_url": "https://coqui.gateway.scarf.sh/v0.10.1_models/tts_models--fa--custom--glow-tts.zip",
|
|
"default_vocoder": null,
|
|
"commit": null,
|
|
"description": "persian-tts-female-glow_tts model for text to speech purposes. Single-speaker female voice Trained on persian-tts-dataset-famale. \nThis model has no compatible vocoder thus the output quality is not very good. \nDataset: https://www.kaggle.com/datasets/magnoliasis/persian-tts-dataset-famale.",
|
|
"author": "@karim23657",
|
|
"license": "CC-BY-4.0"
|
|
}
|
|
}
|
|
},
|
|
"bn": {
|
|
"custom": {
|
|
"vits-male": {
|
|
"github_rls_url": "https://coqui.gateway.scarf.sh/v0.13.3_models/tts_models--bn--custom--vits_male.zip",
|
|
"default_vocoder": null,
|
|
"commit": null,
|
|
"description": "Single speaker Bangla male model. For more information -> https://github.com/mobassir94/comprehensive-bangla-tts",
|
|
"author": "@mobassir94",
|
|
"license": "Apache 2.0"
|
|
},
|
|
"vits-female": {
|
|
"github_rls_url": "https://coqui.gateway.scarf.sh/v0.13.3_models/tts_models--bn--custom--vits_female.zip",
|
|
"default_vocoder": null,
|
|
"commit": null,
|
|
"description": "Single speaker Bangla female model. For more information -> https://github.com/mobassir94/comprehensive-bangla-tts",
|
|
"author": "@mobassir94",
|
|
"license": "Apache 2.0"
|
|
}
|
|
}
|
|
},
|
|
"be": {
|
|
"common-voice": {
|
|
"glow-tts":{
|
|
"description": "Belarusian GlowTTS model created by @alex73 (Github).",
|
|
"github_rls_url":"https://coqui.gateway.scarf.sh/v0.16.6/tts_models--be--common-voice--glow-tts.zip",
|
|
"default_vocoder": "vocoder_models/be/common-voice/hifigan",
|
|
"commit": "c0aabb85",
|
|
"license": "CC-BY-SA 4.0",
|
|
"contact": "alex73mail@gmail.com"
|
|
}
|
|
}
|
|
}
|
|
},
|
|
"vocoder_models": {
|
|
"universal": {
|
|
"libri-tts": {
|
|
"wavegrad": {
|
|
"github_rls_url": "https://coqui.gateway.scarf.sh/v0.6.1_models/vocoder_models--universal--libri-tts--wavegrad.zip",
|
|
"commit": "ea976b0",
|
|
"author": "Eren Gölge @erogol",
|
|
"license": "MPL",
|
|
"contact": "egolge@coqui.com"
|
|
},
|
|
"fullband-melgan": {
|
|
"github_rls_url": "https://coqui.gateway.scarf.sh/v0.6.1_models/vocoder_models--universal--libri-tts--fullband-melgan.zip",
|
|
"commit": "4132240",
|
|
"author": "Eren Gölge @erogol",
|
|
"license": "MPL",
|
|
"contact": "egolge@coqui.com"
|
|
}
|
|
}
|
|
},
|
|
"en": {
|
|
"ek1": {
|
|
"wavegrad": {
|
|
"description": "EK1 en-rp wavegrad by NMStoker",
|
|
"github_rls_url": "https://coqui.gateway.scarf.sh/v0.6.1_models/vocoder_models--en--ek1--wavegrad.zip",
|
|
"commit": "c802255",
|
|
"license": "apache 2.0"
|
|
}
|
|
},
|
|
"ljspeech": {
|
|
"multiband-melgan": {
|
|
"github_rls_url": "https://coqui.gateway.scarf.sh/v0.6.1_models/vocoder_models--en--ljspeech--multiband-melgan.zip",
|
|
"commit": "ea976b0",
|
|
"author": "Eren Gölge @erogol",
|
|
"license": "MPL",
|
|
"contact": "egolge@coqui.com"
|
|
},
|
|
"hifigan_v2": {
|
|
"description": "HiFiGAN_v2 LJSpeech vocoder from https://arxiv.org/abs/2010.05646.",
|
|
"github_rls_url": "https://coqui.gateway.scarf.sh/v0.6.1_models/vocoder_models--en--ljspeech--hifigan_v2.zip",
|
|
"commit": "bae2ad0f",
|
|
"author": "@erogol",
|
|
"license": "apache 2.0",
|
|
"contact": "egolge@coqui.ai"
|
|
},
|
|
"univnet": {
|
|
"description": "UnivNet model finetuned on TacotronDDC_ph spectrograms for better compatibility.",
|
|
"github_rls_url": "https://coqui.gateway.scarf.sh/v0.6.1_models/vocoder_models--en--ljspeech--univnet_v2.zip",
|
|
"commit": "4581e3d",
|
|
"author": "Eren @erogol",
|
|
"license": "apache 2.0",
|
|
"contact": "egolge@coqui.ai"
|
|
}
|
|
},
|
|
"blizzard2013": {
|
|
"hifigan_v2": {
|
|
"description": "HiFiGAN_v2 LJSpeech vocoder from https://arxiv.org/abs/2010.05646.",
|
|
"github_rls_url": "https://coqui.gateway.scarf.sh/v0.7.0_models/vocoder_models--en--blizzard2013--hifigan_v2.zip",
|
|
"commit": "d6284e7",
|
|
"author": "Adam Froghyar @a-froghyar",
|
|
"license": "apache 2.0",
|
|
"contact": "adamfroghyar@gmail.com"
|
|
}
|
|
},
|
|
"vctk": {
|
|
"hifigan_v2": {
|
|
"description": "Finetuned and intended to be used with tts_models/en/vctk/sc-glow-tts",
|
|
"github_rls_url": "https://coqui.gateway.scarf.sh/v0.6.1_models/vocoder_models--en--vctk--hifigan_v2.zip",
|
|
"commit": "2f07160",
|
|
"author": "Edresson Casanova",
|
|
"license": "apache 2.0",
|
|
"contact": ""
|
|
}
|
|
},
|
|
"sam": {
|
|
"hifigan_v2": {
|
|
"description": "Finetuned and intended to be used with tts_models/en/sam/tacotron_DDC",
|
|
"github_rls_url": "https://coqui.gateway.scarf.sh/v0.6.1_models/vocoder_models--en--sam--hifigan_v2.zip",
|
|
"commit": "2f07160",
|
|
"author": "Eren Gölge @erogol",
|
|
"license": "apache 2.0",
|
|
"contact": "egolge@coqui.ai"
|
|
}
|
|
}
|
|
},
|
|
"nl": {
|
|
"mai": {
|
|
"parallel-wavegan": {
|
|
"github_rls_url": "https://coqui.gateway.scarf.sh/v0.6.1_models/vocoder_models--nl--mai--parallel-wavegan.zip",
|
|
"author": "@r-dh",
|
|
"license": "apache 2.0",
|
|
"commit": "unknown"
|
|
}
|
|
}
|
|
},
|
|
"de": {
|
|
"thorsten": {
|
|
"wavegrad": {
|
|
"github_rls_url": "https://coqui.gateway.scarf.sh/v0.6.1_models/vocoder_models--de--thorsten--wavegrad.zip",
|
|
"author": "@thorstenMueller",
|
|
"license": "apache 2.0",
|
|
"commit": "unknown"
|
|
},
|
|
"fullband-melgan": {
|
|
"github_rls_url": "https://coqui.gateway.scarf.sh/v0.6.1_models/vocoder_models--de--thorsten--fullband-melgan.zip",
|
|
"author": "@thorstenMueller",
|
|
"license": "apache 2.0",
|
|
"commit": "unknown"
|
|
},
|
|
"hifigan_v1": {
|
|
"github_rls_url": "https://coqui.gateway.scarf.sh/v0.8.0_models/vocoder_models--de--thorsten--hifigan_v1.zip",
|
|
"description": "HifiGAN vocoder model for Thorsten Neutral Dec2021 22k Samplerate Tacotron2 DDC model",
|
|
"author": "@thorstenMueller",
|
|
"license": "apache 2.0",
|
|
"commit": "unknown"
|
|
}
|
|
}
|
|
},
|
|
"ja": {
|
|
"kokoro": {
|
|
"hifigan_v1": {
|
|
"github_rls_url": "https://coqui.gateway.scarf.sh/v0.6.1_models/vocoder_models--ja--kokoro--hifigan_v1.zip",
|
|
"description": "HifiGAN model trained for kokoro dataset by @kaiidams",
|
|
"author": "@kaiidams",
|
|
"license": "apache 2.0",
|
|
"commit": "3900448"
|
|
}
|
|
}
|
|
},
|
|
"uk": {
|
|
"mai": {
|
|
"multiband-melgan": {
|
|
"github_rls_url": "https://coqui.gateway.scarf.sh/v0.6.1_models/vocoder_models--uk--mai--multiband-melgan.zip",
|
|
"author": "@robinhad",
|
|
"commit": "bdab788d",
|
|
"license": "MIT",
|
|
"contact": ""
|
|
}
|
|
}
|
|
},
|
|
"tr": {
|
|
"common-voice": {
|
|
"hifigan": {
|
|
"github_rls_url": "https://coqui.gateway.scarf.sh/v0.6.1_models/vocoder_models--tr--common-voice--hifigan.zip",
|
|
"description": "HifiGAN model using an unknown speaker from the Common-Voice dataset.",
|
|
"author": "Fatih Akademi",
|
|
"license": "MIT",
|
|
"commit": null
|
|
}
|
|
}
|
|
},
|
|
"be": {
|
|
"common-voice": {
|
|
"hifigan": {
|
|
"github_rls_url": "https://coqui.gateway.scarf.sh/v0.16.6/vocoder_models--be--common-voice--hifigan.zip",
|
|
"description": "Belarusian HiFiGAN model created by @alex73 (Github).",
|
|
"author": "@alex73",
|
|
"license": "CC-BY-SA 4.0",
|
|
"commit": "c0aabb85"
|
|
}
|
|
}
|
|
}
|
|
},
|
|
"voice_conversion_models": {
|
|
"multilingual": {
|
|
"vctk": {
|
|
"freevc24": {
|
|
"github_rls_url": "https://coqui.gateway.scarf.sh/v0.13.0_models/voice_conversion_models--multilingual--vctk--freevc24.zip",
|
|
"description": "FreeVC model trained on VCTK dataset from https://github.com/OlaWod/FreeVC",
|
|
"author": "Jing-Yi Li @OlaWod",
|
|
"license": "MIT",
|
|
"commit": null
|
|
}
|
|
}
|
|
}
|
|
}
|
|
}
|