Downloads · 30 days
0
Amphion-NaturalSpeech2-Wenetspeech4TTS
Wenetspeech4TTS/Amphion-NaturalSpeech2-Wenetspeech4TTS
Amphion-NaturalSpeech2-Wenetspeech4TTS is a text-to-speech model from Wenetspeech4TTS. Use it when you need text read aloud. The card lists the license as mit.
The entire training process follows its training code, except that the text-to-phoneme feature step and text encoder are slightly different.
Access
Public
Updated Aug 31, 2024
Repo size
4.7 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin4.7 GB · 100%
At a glance
- Task
- Text-to-Speech
- License
- mit
- Access
- Public
- Created
- Jun 6, 2024
- Updated
- Aug 31, 2024
- SHA
- aa59f101
Datasets
Model card
From the Hugging Face model README
The vanilla NaturalSpeech2 train on WenetSpeech4TTS using Amphion tooltik.
The entire training process follows its training code, except that the text-to-phoneme feature step and text encoder are slightly different.
Checkpoints
- ns2_base_model.bin : NaturalSpeech2 trained with the WenetSpeech4TTS Basic subset
- ns2_38_model.bin : NaturalSpeech2 Basic fine-tuning with the WenetSpeech4TTS Standard subset
- ns2_4_model.bin : NaturalSpeech2 Standard fine-tuning with the WenetSpeech4TTS Premium subset
usage
coming soon.
- Task
- Text-to-Speech
- License
- mit
- Languages
- zh
- Created
- Jun 6, 2024
- Updated
- Aug 31, 2024