Add neon models (#2140)

* Add neon ljspeech vits model

* Add neon german model

* Update .models.json

* Add neon spanish model

* Add french model

* Add Dutch model

* Add Hungarian model

* Add Greek model

* Remove uneeded description

* Update .models.json

* Update .models.json

* Handling neon models

* Add all neon models

* Update .models.json

* Split zoo_tests

* Update test names

* Update model testing

Co-authored-by: Eren Gölge <erogol@hotmail.com>
This commit is contained in:
logan hart
2022-11-16 16:12:39 +01:00
committed by GitHub
co-authored by Eren Gölge
parent a0f31df481
commit ff9b63d02a
6 changed files with 385 additions and 14 deletions
+252 -3
View File
@@ -12,6 +12,61 @@
}
}
},
"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": {
@@ -79,6 +134,14 @@
"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",
@@ -151,18 +214,36 @@
"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": "",
"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":{
@@ -174,6 +255,13 @@
"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"
}
}
},
@@ -198,6 +286,15 @@
"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": {
@@ -224,6 +321,15 @@
"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": {
@@ -359,6 +465,149 @@
"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"
}
}
}
},
"vocoder_models": {
@@ -512,4 +761,4 @@
}
}
}
}
}
+11 -2
View File
@@ -213,7 +213,12 @@ class Synthesizer(object):
speaker_embedding = None
speaker_id = None
if self.tts_speakers_file or hasattr(self.tts_model.speaker_manager, "name_to_id"):
if speaker_name and isinstance(speaker_name, str):
# handle Neon models with single speaker.
if len(self.tts_model.speaker_manager.name_to_id) == 1:
speaker_id = list(self.tts_model.speaker_manager.name_to_id.values())[0]
elif speaker_name and isinstance(speaker_name, str):
if self.tts_config.use_d_vector_file:
# get the average speaker embedding from the saved d_vectors.
speaker_embedding = self.tts_model.speaker_manager.get_mean_embedding(
@@ -243,7 +248,11 @@ class Synthesizer(object):
if self.tts_languages_file or (
hasattr(self.tts_model, "language_manager") and self.tts_model.language_manager is not None
):
if language_name and isinstance(language_name, str):
if len(self.tts_model.language_manager.name_to_id) == 1:
language_id = list(self.tts_model.language_manager.name_to_id.values())[0]
elif language_name and isinstance(language_name, str):
language_id = self.tts_model.language_manager.name_to_id[language_name]
elif not language_name: