hailin
/
taixf
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

config: switch to Qwen3-TTS 0.6B for faster inference

This commit is contained in:
hailin 2026-04-07 08:55:08 -07:00
parent 2ec0dcf401
commit 912b54547a
1 changed files with 2 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
config/.config.yaml
View File

@ -23,7 +23,7 @@ wakeup_words:
selected_module:
LLM: antaf
TTS: sherpa_tts
TTS: qwen3_tts
ASR: qwen3_asr_local
LLM:
@ -40,7 +40,7 @@ LLM:
TTS:
qwen3_tts:
type: qwen3_tts
model_path: /home/ZeroStack/xiaozhi/Qwen3-TTS-12Hz-1.7B-CustomVoice
model_path: /home/ZeroStack/xiaozhi/Qwen3-TTS-12Hz-0.6B-CustomVoice
tokenizer_path: /home/ZeroStack/xiaozhi/Qwen3-TTS-Tokenizer-12Hz
device: cuda:2
dtype: bfloat16