diff --git a/TTS/.models.json b/TTS/.models.json index 85a646e6..6ba67b01 100644 --- a/TTS/.models.json +++ b/TTS/.models.json @@ -1,7 +1,7 @@ { - "tts_models":{ - "en":{ - "ek1":{ + "tts_models": { + "en": { + "ek1": { "tacotron2": { "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", @@ -9,7 +9,7 @@ "commit": "c802255" } }, - "ljspeech":{ + "ljspeech": { "tacotron2-DDC": { "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", @@ -17,9 +17,18 @@ "commit": "bae2ad0f", "author": "Eren Gölge @erogol", "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": "", "github_rls_url": "https://github.com/coqui-ai/TTS/releases/download/v0.0.9/tts_models--en--ljspeech--glow-tts.zip", "stats_file": null, @@ -27,7 +36,7 @@ "commit": "", "author": "Eren Gölge @erogol", "license": "MPL", - "contact":"egolge@coqui.com" + "contact": "egolge@coqui.com" }, "tacotron2-DCA": { "description": "", @@ -36,19 +45,28 @@ "commit": "", "author": "Eren Gölge @erogol", "license": "MPL", - "contact":"egolge@coqui.com" + "contact": "egolge@coqui.com" }, - "speedy-speech-wn":{ + "speedy-speech-wn": { "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", "default_vocoder": "vocoder_models/en/ljspeech/multiband-melgan", "commit": "77b6145", "author": "Eren Gölge @erogol", "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": { "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", @@ -56,12 +74,19 @@ "commit": "b531fa69", "author": "Edresson Casanova", "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": { "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", @@ -69,37 +94,37 @@ "commit": "bae2ad0f", "author": "Eren Gölge @erogol", "license": "", - "contact":"egolge@coqui.com" + "contact": "egolge@coqui.com" } } }, - "es":{ - "mai":{ - "tacotron2-DDC":{ + "es": { + "mai": { + "tacotron2-DDC": { "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", "commit": "", "author": "Eren Gölge @erogol", "license": "MPL", - "contact":"egolge@coqui.com" + "contact": "egolge@coqui.com" } } }, - "fr":{ - "mai":{ - "tacotron2-DDC":{ + "fr": { + "mai": { + "tacotron2-DDC": { "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", "commit": "", "author": "Eren Gölge @erogol", "license": "MPL", - "contact":"egolge@coqui.com" + "contact": "egolge@coqui.com" } } }, - "zh-CN":{ - "baker":{ - "tacotron2-DDC-GST":{ + "zh-CN": { + "baker": { + "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", "commit": "unknown", "author": "@kirianguiller", @@ -107,9 +132,9 @@ } } }, - "nl":{ - "mai":{ - "tacotron2-DDC":{ + "nl": { + "mai": { + "tacotron2-DDC": { "github_rls_url": "https://github.com/coqui-ai/TTS/releases/download/v0.0.10/tts_models--nl--mai--tacotron2-DDC.zip", "author": "@r-dh", "default_vocoder": "vocoder_models/nl/mai/parallel-wavegan", @@ -118,9 +143,9 @@ } } }, - "de":{ - "thorsten":{ - "tacotron2-DCA":{ + "de": { + "thorsten": { + "tacotron2-DCA": { "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", "author": "@thorstenMueller", @@ -128,9 +153,9 @@ } } }, - "ja":{ - "kokoro":{ - "tacotron2-DDC":{ + "ja": { + "kokoro": { + "tacotron2-DDC": { "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", "description": "Tacotron2 with Double Decoder Consistency trained with Kokoro Speech Dataset.", @@ -140,54 +165,62 @@ } } }, - "vocoder_models":{ - "universal":{ - "libri-tts":{ - "wavegrad":{ + "vocoder_models": { + "universal": { + "libri-tts": { + "wavegrad": { "github_rls_url": "https://github.com/coqui-ai/TTS/releases/download/v0.0.9/vocoder_models--universal--libri-tts--wavegrad.zip", "commit": "ea976b0", "author": "Eren Gölge @erogol", "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", "commit": "4132240", "author": "Eren Gölge @erogol", "license": "MPL", - "contact":"egolge@coqui.com" + "contact": "egolge@coqui.com" } } }, "en": { - "ek1":{ + "ek1": { "wavegrad": { "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", "commit": "c802255" } }, - "ljspeech":{ - "multiband-melgan":{ + "ljspeech": { + "multiband-melgan": { "github_rls_url": "https://github.com/coqui-ai/TTS/releases/download/v0.0.9/vocoder_models--en--ljspeech--mulitband-melgan.zip", "commit": "ea976b0", "author": "Eren Gölge @erogol", "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.", "github_rls_url": "https://github.com/coqui-ai/TTS/releases/download/v0.0.12/vocoder_model--en--ljspeech-hifigan_v2.zip", "commit": "bae2ad0f", "author": "@erogol", "license": "", "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":{ - "hifigan_v2":{ + "vctk": { + "hifigan_v2": { "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", "author": "Edresson Casanova", "license": "", @@ -195,9 +228,9 @@ } }, "sam": { - "hifigan_v2":{ + "hifigan_v2": { "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", "author": "Eren Gölge @erogol", "license": "", @@ -205,28 +238,38 @@ } } }, - "nl":{ - "mai":{ - "parallel-wavegan":{ + "nl": { + "mai": { + "parallel-wavegan": { "github_rls_url": "https://github.com/coqui-ai/TTS/releases/download/v0.0.10/vocoder_models--nl--mai--parallel-wavegan.zip", "author": "@r-dh", "commit": "unknown" } } }, - "de":{ - "thorsten":{ - "wavegrad":{ + "de": { + "thorsten": { + "wavegrad": { "github_rls_url": "https://github.com/coqui-ai/TTS/releases/download/v0.0.11/vocoder_models--de--thorsten--wavegrad.zip", "author": "@thorstenMueller", "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", "author": "@thorstenMueller", "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" + } + } } } -} +} \ No newline at end of file