Dubsweet TTS models (GGUF)
GGUF conversions of Qwen/Qwen3-TTS-12Hz-1.7B-Base (revision fd4b254), used by Dubsweet's local TTS engine.
Changes from the original: talker weights converted safetensors -> GGUF (bf16); speech tokenizer converted to GGUF (f16). No weight values were modified.
Licensed under Apache 2.0, same as the source model.
- Downloads last month
- 16
Hardware compatibility
Log In to add your hardware
16-bit
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for thecargocult/dubsweet-tts-models
Base model
Qwen/Qwen3-TTS-12Hz-1.7B-Base