mirror of https://github.com/coqui-ai/TTS.git
377 lines
17 KiB
JSON
377 lines
17 KiB
JSON
{
|
|
"tts_models": {
|
|
"multilingual":{
|
|
"multi-dataset":{
|
|
"your_tts":{
|
|
"description": "Your TTS model accompanying the paper https://arxiv.org/abs/2112.02418",
|
|
"github_rls_url": "https://coqui.gateway.scarf.sh/v0.6.1_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"
|
|
}
|
|
}
|
|
},
|
|
"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"
|
|
}
|
|
},
|
|
"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": "",
|
|
"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": "",
|
|
"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": "TBD",
|
|
"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": "TBD",
|
|
"contact": "egolge@coqui.com"
|
|
},
|
|
"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": "TBD",
|
|
"contact": "egolge@coqui.com"
|
|
}
|
|
},
|
|
"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": "",
|
|
"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": "",
|
|
"contact": "egolge@coqui.com"
|
|
}
|
|
}
|
|
},
|
|
"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"
|
|
}
|
|
}
|
|
},
|
|
"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": "",
|
|
"author": "Eren Gölge @erogol",
|
|
"license": "MPL",
|
|
"contact": "egolge@coqui.com"
|
|
}
|
|
}
|
|
},
|
|
"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"
|
|
}
|
|
}
|
|
},
|
|
"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",
|
|
"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",
|
|
"default_vocoder": "vocoder_models/nl/mai/parallel-wavegan",
|
|
"stats_file": null,
|
|
"commit": "540d811"
|
|
}
|
|
}
|
|
},
|
|
"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",
|
|
"commit": "unknown"
|
|
}
|
|
}
|
|
},
|
|
"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",
|
|
"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",
|
|
"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",
|
|
"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",
|
|
"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",
|
|
"commit": null
|
|
}
|
|
}
|
|
}
|
|
},
|
|
"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"
|
|
}
|
|
},
|
|
"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": "",
|
|
"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": "TBD",
|
|
"contact": "egolge@coqui.ai"
|
|
}
|
|
},
|
|
"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": "",
|
|
"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": "",
|
|
"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",
|
|
"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",
|
|
"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",
|
|
"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",
|
|
"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
|
|
}
|
|
}
|
|
}
|
|
}
|
|
} |