Downloads · 30 days
0
Malaysian-F5-TTS-v2
mesolitica/Malaysian-F5-TTS-v2
Malaysian-F5-TTS-v2 is a machine learning model from mesolitica. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as cc-by-nc-4.0.
Continue training from SWivid/F5-TTS F5TTSBase checkpoint on Malaysian-Emilia,
Access
Public
Updated Mar 30, 2025
Repo size
58 GB
Likes
2
Public
Repo makeup
Click a slice to open those files.
.pt28.3 GB · 100%
At a glance
- License
- cc-by-nc-4.0
- Access
- Public
- Created
- Jan 14, 2025
- Updated
- Mar 30, 2025
- SHA
- 1aa30e4a
Base models
Datasets
Model card
From the Hugging Face model README
Full Parameter Finetuning Malaysian Emilia F5-TTS v2
Continue training from SWivid/F5-TTS F5TTS_Base checkpoint on Malaysian-Emilia,
with total 8472 hours included 600 hours Mandarin sampled from amphion/Emilia-Dataset.
Features
- This model should be able to zero-shot voice conversion any Malaysian and Singaporean speakers.
- This model able to generate minimal filler sounds such as
erm,huh, for example below,
<audio controls src="https://cdn-uploads.huggingface.co/production/uploads/5e73316106936008a9ee6523/qoFxdAgPkxTxsNxrbdjs_.wav"></audio>
Isu sekarangnya, erm, kita harus jadi yang terbaik untuk rakyat Malaysia, dan kita, uh, kena makan nasi lemak yang sedap lagi lazat, hah, penat nak kena cakap.
Checkpoints
We uploaded full checkpoints with optimizer states at checkpoints.
Dataset
We train on postfilter Malaysian-Emilia called Malaysian-Voice-Conversion
Source code
All source code at https://github.com/mesolitica/malaya-speech/tree/master/session/f5-tts
- License
- cc-by-nc-4.0
- Languages
- ms, en
- Created
- Jan 14, 2025
- Updated
- Mar 30, 2025