anodyine/vllm-omni
1
0 Fork 0
Code Issues 4 Pull Requests 2 Actions Packages Projects Releases Wiki Activity

[Feat][Qwen3TTS] reduce TTFA with flexible initial phase (#1583)

Browse Source 
Signed-off-by: pablo <pablo@agigo.ai>
Co-authored-by: pablo <pablo@agigo.ai>
This commit is contained in:
Juan Pablo Zuluagaandpablo authored and GitHub committed 2026-03-05 23:14:41 +08:00
1 parent 070ea0ddc3
commit 6a45efb287
14 files changed
+202 -44
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

docs/user_guide/examples/offline_inference/qwen3_tts.md
+2 -1
View File
@@ -98,7 +98,8 @@ Add `--streaming` to stream audio chunks progressively via `AsyncOmni` (requires
python end2end.py --query-type CustomVoice --streaming --output-dir /tmp/out_stream
```
Each 25-frame Code2Wav chunk is logged as it arrives. The final WAV file is written once generation
Each Code2Wav chunk is logged as it arrives (default 25 frames; configurable via `codec_chunk_frames`
and `initial_codec_chunk_frames` in the stage config). The final WAV file is written once generation
completes. This demonstrates that audio data is available progressively rather than only at the end.
> **Note:** Streaming uses `AsyncOmni` internally. The non-streaming path (`Omni`) is unchanged.