cr2k2
/

Qwen3-TTS-12Hz-1.7B-Base-fp32

Model card Files Files and versions

Qwen3-TTS-12Hz-1.7B-Base-fp32

4.54 GB

Ctrl+K

Ctrl+K

1 contributor

History: 4 commits

cr2k2's picture

Upload folder using huggingface_hub

143166c verified 2 months ago

speech_tokenizer
MLX fp32 conversion of Qwen3-TTS-12Hz-1.7B-Base — same speed as bf16 on Apple Silicon, better quality 2 months ago
.gitattributes

1.52 kB
initial commit 2 months ago
README.md

3.16 kB
Upload folder using huggingface_hub 2 months ago
config.json

5.32 kB
MLX fp32 conversion of Qwen3-TTS-12Hz-1.7B-Base — same speed as bf16 on Apple Silicon, better quality 2 months ago
generation_config.json

245 Bytes
MLX fp32 conversion of Qwen3-TTS-12Hz-1.7B-Base — same speed as bf16 on Apple Silicon, better quality 2 months ago
merges.txt

1.67 MB
MLX fp32 conversion of Qwen3-TTS-12Hz-1.7B-Base — same speed as bf16 on Apple Silicon, better quality 2 months ago
model.safetensors

3.86 GB
LFS

MLX fp32 conversion of Qwen3-TTS-12Hz-1.7B-Base — same speed as bf16 on Apple Silicon, better quality 2 months ago
model.safetensors.index.json

38.7 kB
MLX fp32 conversion of Qwen3-TTS-12Hz-1.7B-Base — same speed as bf16 on Apple Silicon, better quality 2 months ago
preprocessor_config.json

127 Bytes
MLX fp32 conversion of Qwen3-TTS-12Hz-1.7B-Base — same speed as bf16 on Apple Silicon, better quality 2 months ago
tokenizer_config.json

7.34 kB
MLX fp32 conversion of Qwen3-TTS-12Hz-1.7B-Base — same speed as bf16 on Apple Silicon, better quality 2 months ago
vocab.json

2.78 MB
MLX fp32 conversion of Qwen3-TTS-12Hz-1.7B-Base — same speed as bf16 on Apple Silicon, better quality 2 months ago