verachen/Qwen3-ASR
1
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity

fix: uv dependency
All checks were successful
Build container / build-docker (push) Successful in 24m10s
Details

Browse Source
This commit is contained in:
vera
2026-04-23 10:07:20 +08:00
parent 42eb035f4b
commit 7231ed2354
3 changed files with 5 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
Dockerfile
View File

@ -7,6 +7,7 @@ COPY --from=ghcr.io/astral-sh/uv:latest /uv /uvx /bin/
WORKDIR /app WORKDIR /app
COPY . . COPY . .
RUN uv sync RUN uv sync
RUN uv sync --extra vllm
ENV ASR_MODEL_PATH="Qwen/Qwen3-ASR-1.7B" ENV ASR_MODEL_PATH="Qwen/Qwen3-ASR-1.7B"

6
README_BW.md
View File

@ -19,14 +19,14 @@ https://github.com/QwenLM/Qwen3-ASR
# Start # Start
```bash ```bash
docker pull harbor.bwgdi.com/library/qwen3asr:0.0.1 docker pull harbor.bwgdi.com/library/qwen3-asr:0.0.1
# Run with custom model path # Run with custom model path
# -e ASR_MODEL_PATH: Model name or local path inside container # -e ASR_MODEL_PATH: Model name or local path inside container
docker run -d --restart always -p 8000:8000 --gpus all \ docker run -d --restart always -p 5051:5000 --gpus all \
-e ASR_MODEL_PATH="Qwen/Qwen3-ASR-1.7B" \ -e ASR_MODEL_PATH="Qwen/Qwen3-ASR-1.7B" \
--mount type=bind,source=/path/to/your/models,target=/models \ --mount type=bind,source=/path/to/your/models,target=/models \
harbor.bwgdi.com/library/qwen3asr:0.0.3 harbor.bwgdi.com/library/qwen3-asr:0.0.1
``` ```
# Usage # Usage

2
examples/api_unified_fastapi.py
View File

@ -173,7 +173,7 @@ def parse_args():
p = argparse.ArgumentParser(description="Qwen3-ASR Unified API (streaming + non-streaming)") p = argparse.ArgumentParser(description="Qwen3-ASR Unified API (streaming + non-streaming)")
p.add_argument("--asr-model-path", default="Qwen/Qwen3-ASR-1.7B", help="Model name or local path") p.add_argument("--asr-model-path", default="Qwen/Qwen3-ASR-1.7B", help="Model name or local path")
p.add_argument("--host", default="0.0.0.0") p.add_argument("--host", default="0.0.0.0")
p.add_argument("--port", type=int, default=8000) p.add_argument("--port", type=int, default=5000)
p.add_argument("--gpu-memory-utilization", type=float, default=0.8) p.add_argument("--gpu-memory-utilization", type=float, default=0.8)
p.add_argument("--max-new-tokens", type=int, default=32, p.add_argument("--max-new-tokens", type=int, default=32,
help="Max new tokens per call (streaming). Use larger value for non-streaming.") help="Max new tokens per call (streaming). Use larger value for non-streaming.")