4.15 GB

Ctrl+K

2 contributors

Update all 34 language/gender LoRA adapters: 15 new languages (60s-packed data, LR=1e-7) + refreshed telugu/punjabi checkpoints

5450c7f verified about 2 months ago

adapters
Update all 34 language/gender LoRA adapters: 15 new languages (60s-packed data, LR=1e-7) + refreshed telugu/punjabi checkpoints about 2 months ago
speech_tokenizer
Add Qwen3-TTS-0.6B base model weights and speech tokenizer for standalone loading about 2 months ago
.gitattributes

3.78 kB
Update all 34 language/gender LoRA adapters: 15 new languages (60s-packed data, LR=1e-7) + refreshed telugu/punjabi checkpoints about 2 months ago
README.md

8.39 kB
Add notebook inference example and README link about 2 months ago
config.json

4.49 kB
Add Qwen3-TTS-0.6B base model weights and speech tokenizer for standalone loading about 2 months ago
generation_config.json

245 Bytes
Add Qwen3-TTS-0.6B base model weights and speech tokenizer for standalone loading about 2 months ago
merges.txt

1.67 MB
Add Qwen3-TTS-0.6B base model weights and speech tokenizer for standalone loading about 2 months ago
model.safetensors

1.83 GB
xet

Add Qwen3-TTS-0.6B base model weights and speech tokenizer for standalone loading about 2 months ago
notebook.ipynb

24.6 kB
Rename Qwen3_TTS_Indic_Inference.ipynb to notebook.ipynb about 2 months ago
preprocessor_config.json

127 Bytes
Add Qwen3-TTS-0.6B base model weights and speech tokenizer for standalone loading about 2 months ago
tokenizer_config.json

7.34 kB
Add Qwen3-TTS-0.6B base model weights and speech tokenizer for standalone loading about 2 months ago
vocab.json

2.78 MB
Add Qwen3-TTS-0.6B base model weights and speech tokenizer for standalone loading about 2 months ago