Irodori-TTS-600M-v3-VoiceDesign — fp16 (MLX)
MLX-quantized (fp16) fork of Aratako/Irodori-TTS (MIT).
Japanese Flow-Matching TTS, 48 kHz. DACVAE is kept unquantized.
- Downloads last month
- 34
Model size
0.6B params
Tensor type
F16
·
Hardware compatibility
Log In to add your hardware
Quantized
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for tkysdev/Irodori-TTS-600M-v3-VoiceDesign-fp16
Base model
Aratako/Irodori-TTS-500M-v2 Finetuned
Aratako/Irodori-TTS-600M-v3-VoiceDesign