EZ-Voice-Clone-EZ / speakers.json
Omnibus's picture
Create speakers.json
185654b verified
raw
history blame
9.1 kB
"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"
}
}
},