mlx-community/Irodori-TTS-500M-v3-fp16
Japanese TTS model converted to MLX fp16 format from Aratako/Irodori-TTS-500M-v3 using mlx-audio v0.4.3.
Features (v3)
- Duration predictor: automatically estimates output length — no need to specify
- Sway Sampling: non-linear timestep schedule for better quality with fewer steps
- Voice cloning: optional for speaker style transfer
- Backward compatible: v2 checkpoints continue to work
Available variants
| Model | Size | Memory |
|---|---|---|
| mlx-community/Irodori-TTS-500M-v3-fp16 (this) | 977 MB | ~4.3 GB |
| mlx-community/Irodori-TTS-500M-v3-8bit | 663 MB | ~4.0 GB |
Use with mlx-audio
Command line
Python
- Downloads last month
- 8
Model size
0.5B params
Tensor type
F16
·
Hardware compatibility
Log In to add your hardware
Quantized
Model tree for mlx-community/Irodori-TTS-500M-v3-fp16
Base model
Aratako/Irodori-TTS-500M-v2 Finetuned
Aratako/Irodori-TTS-500M-v3