Downloads · 30 days
8
5% of all-time downloads
MozillaSpeakerEncoderModels
czyzi0/MozillaSpeakerEncoderModels
MozillaSpeakerEncoderModels is a machine learning model from czyzi0. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for transformers. The card lists the license as mpl-2.0.
This repository contains released Mozilla SpeakerEncoder models.
All-time downloads
166
Public
Repo size
143 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.tar143 MB · 100%
At a glance
- Library
- transformers
- License
- mpl-2.0
- Access
- Public
- Created
- Jul 6, 2024
- Updated
- Jul 7, 2024
- SHA
- 70d4a302
Model card
From the Hugging Face model README
This repository contains released Mozilla SpeakerEncoder models.
Due to original codebase migration and SpeakerEncoder depracation, I decided to extract inference code into my own repository. For ease of integration, I also release relevant models:
model_mozilla_128.pth.tar- which is Speaker-Encoder-iter25k that was trained on LibriSpeech,model_mozilla_256.pth.tar- which is Speaker-Encoder by @mueller91 that was trained on LibriTTS, VCTK, VoxCeleb and CommonVoice.
Original SpeakerEncoder implementation is available here and originally released models are available here. If you are interested in the current version of Coqui.ai TTS go here.
- Library
- transformers
- License
- mpl-2.0
- Created
- Jul 6, 2024
- Updated
- Jul 7, 2024