mARTin-B78
40786314ef
The upstream openai_server.py removed the instruct parameter from the generate_voice_clone call, breaking the old patch context. Regenerated from a fresh upstream clone with all four changes: - non_streaming_mode=True in _stream_chunks and create_speech - per-voice temperature/top_k/top_p in both generation paths - --max-seq-len argument added to _parse_args - max_seq_len=args.max_seq_len passed to FasterQwen3TTS.from_pretrained Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
44 lines
2.0 KiB
Diff
44 lines
2.0 KiB
Diff
diff --git a/examples/openai_server.py b/examples/openai_server.py
|
|
index 2199e14..cb44644 100644
|
|
--- a/examples/openai_server.py
|
|
+++ b/examples/openai_server.py
|
|
@@ -185,7 +185,10 @@ async def _stream_chunks(voice_cfg: dict, text: str) -> AsyncGenerator[bytes, No
|
|
ref_audio=voice_cfg["ref_audio"],
|
|
ref_text=voice_cfg.get("ref_text", ""),
|
|
chunk_size=voice_cfg.get("chunk_size", 12),
|
|
- non_streaming_mode=False,
|
|
+ non_streaming_mode=True,
|
|
+ temperature=voice_cfg.get("temperature", 0.8),
|
|
+ top_k=voice_cfg.get("top_k", 50),
|
|
+ top_p=voice_cfg.get("top_p", 0.9),
|
|
):
|
|
q.put(chunk)
|
|
except Exception as exc:
|
|
@@ -249,6 +252,10 @@ async def create_speech(req: SpeechRequest):
|
|
language=voice_cfg.get("language", "Auto"),
|
|
ref_audio=voice_cfg["ref_audio"],
|
|
ref_text=voice_cfg.get("ref_text", ""),
|
|
+ non_streaming_mode=True,
|
|
+ temperature=voice_cfg.get("temperature", 0.8),
|
|
+ top_k=voice_cfg.get("top_k", 50),
|
|
+ top_p=voice_cfg.get("top_p", 0.9),
|
|
)
|
|
|
|
audio_arrays, sr = await loop.run_in_executor(None, _generate)
|
|
@@ -306,6 +313,7 @@ def _parse_args():
|
|
p.add_argument("--host", default="0.0.0.0", help="Bind host (default: 0.0.0.0)")
|
|
p.add_argument("--port", type=int, default=8000, help="Bind port (default: 8000)")
|
|
p.add_argument("--device", default="cuda", help="Torch device (default: cuda)")
|
|
+ p.add_argument("--max-seq-len", type=int, default=4096, help="Max sequence length for CUDA graph static cache (default: 4096)")
|
|
return p.parse_args()
|
|
|
|
|
|
@@ -344,6 +352,7 @@ def main():
|
|
args.model,
|
|
device=args.device,
|
|
dtype=torch.bfloat16,
|
|
+ max_seq_len=args.max_seq_len,
|
|
)
|
|
SAMPLE_RATE = tts_model.sample_rate
|
|
logger.info("Model ready. Sample rate: %d Hz", SAMPLE_RATE)
|