Multi-speaker GlowTTS model for Talrómur 2 (prerelease) (22.10)

Gunnarsson, Þorsteinn Daði

dc.contributor.author	Gunnarsson, Þorsteinn Daði
dc.date.accessioned	2022-09-30T15:42:26Z
dc.date.available	2022-09-30T15:42:26Z
dc.date.issued	2022-10-01
dc.identifier.uri	http://hdl.handle.net/20.500.12537/292
dc.description	This release includes a partially trained multi-speaker model using the GlowTTS architecture in the Coqui TTS library [1]. The model is trained on all of the speakers in the Talrómur 2 [2] corpus. The release includes the model, training log, model configuration file and the recipe used to train the model. The model included here is the best model available during the training at the time of publishing. At run time it is possible to choose any of the voices to produce a similar sounding synthesized voice. Þessi útgáfa inniheldur módel þjálfað á mörgum röddum með notkun GlowTTS nálgunarinnar í Coqui TTS verkfærakistunni [1]. Módelið er þjálfað á öllum röddum í Talrómur 2 [2] gagnasafninu. Innifalið í pakkanum er módelið, þjálfunarsaga, skjal með stillingum fyrir módelið og forskriftin sem var notuð til að þjálfa módelið. Módelið sem er hér inni er besta módelið í þjálfunarferlinu á þeim tíma sem þetta er gefið út. Þegar módelið er keyrt er hægt að velja hvaða rödd sem er úr Talrómur 2 gagnasafninu til að búa til upptöku með sambærilegri rödd. [1] https://github.com/cadia-lvl/coqui-ai-TTS/releases/tag/M9 [2] http://hdl.handle.net/20.500.12537/167
dc.language.iso	isl
dc.publisher	Language and Voice Lab, Reykjavík University
dc.rights	Creative Commons - Attribution 4.0 International (CC BY 4.0)
dc.rights.uri	https://creativecommons.org/licenses/by/4.0/
dc.rights.label	PUB
dc.source.uri	https://github.com/cadia-lvl/coqui-ai-TTS/releases/tag/M9
dc.subject	TTS
dc.subject	Text-to-speech
dc.title	Multi-speaker GlowTTS model for Talrómur 2 (prerelease) (22.10)
dc.type	toolService
metashare.ResourceInfo#ContentInfo.detailedType	tool
metashare.ResourceInfo#ResourceComponentType#ToolServiceInfo.languageDependent	true
has.files	yes
branding	Clarin IS Repository
contact.person	Þorsteinn Daði Gunnarsson thorsteinng@ru.is Language and Voice Lab, Reykjavík University
sponsor	The Icelandic Ministry of Education, Science and Culture T13 – Parametric synthesis for Icelandic Language Technology for Icelandic 2019-2023 nationalFunds
files.size	358653753
files.count	2