Skip to content

Open-source speech recognition toolkit for training, inference, streaming ASR, VAD, punctuation, speaker diarization pipelines, and OpenAI-compatible/MCP serving.

Record clean GPU quickstart validation (#3382)

zhifu gao0db97cb81712
diff --git a/docs/community_growth_20k.md b/docs/community_growth_20k.md
index 2e9e228a9..84363b13d 100644
--- a/docs/community_growth_20k.md
+++ b/docs/community_growth_20k.md
@@ -341,7 +341,7 @@ Paste the Markdown output into launch notes, weekly community updates, or releas
### Week 1: Repository conversion
-- [ ] Verify README quick start on clean CPU and GPU environments. On 2026-07-23, clean venv checks covered README Quick Start SenseVoiceSmall CPU and README Quick Start Fun-ASR-Nano GPU setup paths with `torch 2.13.0+cu130`, `torchaudio 2.11.0+cu130`, and `funasr 1.3.26`. The clean CPU venv ran `AutoModel(model="iic/SenseVoiceSmall", vad_model="fsmn-vad", spk_model="cam++", device="cpu")` and produced `欢迎大家来体验达摩院推出的语音识别模型`. The clean GPU venv ran `AutoModel(model="FunAudioLLM/Fun-ASR-Nano-2512", device="cuda")` and produced the same sample text, but `torch.cuda.is_available()` was `False` on an H100 host after the bare `pip install torch torchaudio` path, so README and README_zh now tell GPU users to install the PyTorch / torchaudio CUDA wheels from pytorch.org and verify `torch.cuda.is_available()` before using `device="cuda"`. Do not mark this complete until a clean GPU venv reports CUDA visible. Logs are kept under `/cpfs_speech/user/zhifu.gzf/.cache/funasr-ops/readme-quickstart-cpu-20260723.log` and `/cpfs_speech/user/zhifu.gzf/.cache/funasr-ops/readme-quickstart-gpu-20260723.log`.
+- [x] Verify README quick start on clean CPU and GPU environments. On 2026-07-23, clean venv checks covered README Quick Start SenseVoiceSmall CPU and README Quick Start Fun-ASR-Nano GPU setup paths. The clean CPU venv ran `AutoModel(model="iic/SenseVoiceSmall", vad_model="fsmn-vad", spk_model="cam++", device="cpu")` with `torch 2.13.0+cu130`, `torchaudio 2.11.0+cu130`, and `funasr 1.3.26`, then produced `欢迎大家来体验达摩院推出的语音识别模型`. The first clean GPU venv reproduced the README GPU path with the bare `pip install torch torchaudio`; it installed `torch 2.13.0+cu130` and `torchaudio 2.11.0+cu130`, generated the same Fun-ASR-Nano sample text, but `torch.cuda.is_available()` was `False` on the H100 host. README and README_zh now tell GPU users to install matching PyTorch / torchaudio CUDA wheels from pytorch.org and verify `torch.cuda.is_available()` before using `device="cuda"`. A second clean GPU venv installed explicit cu128 wheels from `https://download.pytorch.org/whl/cu128` and passed end to end with `torch 2.11.0+cu128`, `torch.version.cuda 12.8`, `torchaudio 2.11.0+cu128`, `funasr 1.3.26`, `cuda_available True`, `NVIDIA H100 80GB HBM3`, and `AutoModel(model="FunAudioLLM/Fun-ASR-Nano-2512", device="cuda")` producing `欢迎大家来体验达摩院推出的语音识别模型。` with `rtf_avg: 0.237`. Logs are kept under `/cpfs_speech/user/zhifu.gzf/.cache/funasr-ops/readme-quickstart-cpu-20260723.log`, `/cpfs_speech/user/zhifu.gzf/.cache/funasr-ops/readme-quickstart-gpu-20260723.log`, and `/cpfs_speech/user/zhifu.gzf/.cache/funasr-ops/readme-quickstart-gpu-cu128-20260723.log`.
- [x] Verify high-traffic README, docs, runtime, and model_zoo links. On 2026-07-23, PRs #3360 through #3363 refreshed localized README Paraformer links, runtime tutorial download commands, runtime deploy-script fallback URLs, package/help metadata, model_zoo Hugging Face links, and verified core ModelScope entries; regression guards now cover these public entry points.
- [x] Add or refresh CONTRIBUTING, PR template, and issue templates. On 2026-07-23, the four core repositories now have `CONTRIBUTING.md`, issue templates, and PR templates: `modelscope/FunClip#188`, `modelscope/FunClip#189`, `FunAudioLLM/Fun-ASR#151`, and `FunAudioLLM/SenseVoice#327` closed the remaining gaps after the existing FunASR, Fun-ASR, and SenseVoice templates were audited.
- [x] Add a short FAQ for install/deployment failures. On 2026-07-23, `modelscope/FunASR#3366` added [`docs/troubleshooting.md`](./troubleshooting.md) and [`docs/troubleshooting_zh.md`](./troubleshooting_zh.md), linked both from README and README_zh, and covered `torch` / `torchaudio`, ModelScope versus Hugging Face downloads, `funasr-server` `/v1/audio/transcriptions`, `WebSocket` realtime checks, `llama.cpp` / `GGUF`, and `Deployment Help` issue details.
diff --git a/tests/test_growth_plan_doc.py b/tests/test_growth_plan_doc.py
index 59c516578..165d0cd10 100644
--- a/tests/test_growth_plan_doc.py
+++ b/tests/test_growth_plan_doc.py
@@ -46,27 +46,36 @@ def test_growth_plan_records_readme_quick_start_cpu_gpu_validation():
text = PLAN.read_text()
required_markers = [
- "[ ] Verify README quick start on clean CPU and GPU environments",
+ "[x] Verify README quick start on clean CPU and GPU environments",
"clean CPU venv",
"clean GPU venv",
"README Quick Start SenseVoiceSmall CPU",
"README Quick Start Fun-ASR-Nano GPU",
"`torch 2.13.0+cu130`",
"`torchaudio 2.11.0+cu130`",
+ "`torch 2.11.0+cu128`",
+ "`torch.version.cuda 12.8`",
+ "`torchaudio 2.11.0+cu128`",
"`funasr 1.3.26`",
"`AutoModel(model=\"iic/SenseVoiceSmall\"",
"`AutoModel(model=\"FunAudioLLM/Fun-ASR-Nano-2512\"",
"`torch.cuda.is_available()` was `False`",
- "install the PyTorch / torchaudio CUDA wheels from pytorch.org",
+ "install matching PyTorch / torchaudio CUDA wheels from pytorch.org",
"verify `torch.cuda.is_available()` before using `device=\"cuda\"`",
- "Do not mark this complete until a clean GPU venv reports CUDA visible",
+ "`cuda_available True`",
+ "`NVIDIA H100 80GB HBM3`",
+ "`rtf_avg: 0.237`",
"欢迎大家来体验达摩院推出的语音识别模型",
"readme-quickstart-cpu-20260723.log",
"readme-quickstart-gpu-20260723.log",
+ "readme-quickstart-gpu-cu128-20260723.log",
]
for marker in required_markers:
assert marker in text
+ assert "[ ] Verify README quick start on clean CPU and GPU environments" not in text
+ assert "Do not mark this complete until a clean GPU venv reports CUDA visible" not in text
+
def test_growth_plan_records_github_metadata_completion():
text = PLAN.read_text()