Open-source speech recognition toolkit for training, inference, streaming ASR, VAD, punctuation, speaker diarization pipelines, and OpenAI-compatible/MCP serving.
Python asraudiochineseemotion-recognitionfunasrmcp-servermultilingual-asropenai-compatible-apiparaformerpunctuationpytorchreal-time-asrspeaker-diarizationspeech-recognitionspeech-to-textstreaming-asrtranscriptionvllmvoice-activity-detectionwhisper-alternative
Record release note terminal outputs (#3373)
zhifu gao8d5b10966094
diff --git a/docs/community_growth_20k.md b/docs/community_growth_20k.mdindex f583bb982..76a30f2ef 100644--- a/docs/community_growth_20k.md+++ b/docs/community_growth_20k.md@@ -353,7 +353,7 @@ Paste the Markdown output into launch notes, weekly community updates, or releas- [x] Publish WebSocket streaming examples. On 2026-07-23, realtime WebSocket examples are published in `docs/vllm_guide.md`, `docs/vllm_guide_zh.md`, and `examples/industrial_data_pretraining/fun_asr_nano/docs/realtime_demo.md`. They show how to start `serve_realtime_ws.py`, connect to `ws://localhost:10095`, run `client_python.py --server ws://localhost:10095 --mic` or `client_python.py --server ws://localhost:10095 --file audio.wav`, interpret `partial`, `partial_start_ms`, and `is_final`, and run `realtime_ws_benchmark.py` for multi-client load checks.- [ ] Validate Docker CPU and GPU images. On 2026-07-23, `examples/openai_api/validate_docker.sh` was prepared so a Docker-capable host can run `bash validate_docker.sh` for the portable CPU image and `bash validate_docker.sh --gpu` for the NVIDIA Container Toolkit path. Current ops-host evidence: `ind-gpu8` has H100 GPUs but no `docker` CLI, and `funasr-web` also has no `docker` CLI, so do not mark this item complete until the script passes on a Docker host.- [x] Validate vLLM guide on one GPU server. On 2026-07-23, `ind-gpu8` validated the Fun-ASR-Nano vLLM guide on one H100 with the existing `funasr-3239-vllm0191-py312-20260717` environment (`torch 2.10.0+cu128`, `vllm 0.19.1`, `funasr 1.3.26`, `modelscope 1.38.1`, CUDA available with 8 H100s). The first attempt with the HF `Fun-ASR-Nano-2512-hf` snapshot correctly failed before vLLM init because that Transformers-format snapshot lacks the guide-required `Qwen3-0.6B` directory. The verified run used the ModelScope snapshot with `Qwen3-0.6B` and `model.pt`, then ran `CUDA_VISIBLE_DEVICES=0` `examples/industrial_data_pretraining/fun_asr_nano/demo_vllm.py` with `tensor_parallel_size=1`, `gpu_memory_utilization=0.35`, `max_model_len=1024`, and the bundled `example/zh.mp3`; `model.pt` was converted to `Qwen3-0.6B-vllm/model.safetensors`, vLLM loaded on GPU 0, Model loaded in 82.6s, and inference processed 1 files in 1.95s with output `开饭时间早上九点至下午五点。` plus token timestamps. Logs are kept under `/cpfs_speech/user/zhifu.gzf/.cache/funasr-ops/vllm-guide-smoke-ms-20260723.log` and the JSONL result under `/cpfs_speech/user/zhifu.gzf/.cache/funasr-ops/vllm-guide-smoke-ms-20260723.jsonl`.-- [ ] Record concise terminal outputs for release notes.+- [x] Record concise terminal outputs for release notes. On 2026-07-23, the release-note evidence pack was reduced to four copy-paste terminal snippets: growth snapshot (`Combined GitHub stars: **35,787**`, `Added since baseline: **4,563** / 20,000`, `PyPI package: **funasr 1.3.26**`), live website patrol (`funasr.com static page contract passed for 9 pages`), Docker helper guard (`validate_docker.sh syntax ok`, while full Docker CPU/GPU image validation still waits for a Docker-capable host), and H100 vLLM smoke (`Model loaded in 82.6s`, `Results: 1 samples, total inference time: 1.95s`, `Text: 开饭时间早上九点至下午五点。`). Release notes can now cite the growth snapshot, website patrol, Docker helper guard, and H100 vLLM smoke without pasting long logs.### Week 3: Launch packagediff --git a/tests/test_growth_plan_doc.py b/tests/test_growth_plan_doc.pyindex 470438762..84b05120d 100644--- a/tests/test_growth_plan_doc.py+++ b/tests/test_growth_plan_doc.py@@ -127,3 +127,24 @@ def test_growth_plan_records_vllm_guide_gpu_validation():assert marker in textassert "[ ] Validate vLLM guide on one GPU server" not in text+++def test_growth_plan_records_release_note_terminal_outputs():+ text = PLAN.read_text()++ required_markers = [+ "[x] Record concise terminal outputs for release notes",+ "Combined GitHub stars: **35,787**",+ "Added since baseline: **4,563** / 20,000",+ "PyPI package: **funasr 1.3.26**",+ "funasr.com static page contract passed for 9 pages",+ "validate_docker.sh syntax ok",+ "Model loaded in 82.6s",+ "Results: 1 samples, total inference time: 1.95s",+ "Text: 开饭时间早上九点至下午五点。",+ "Release notes can now cite the growth snapshot, website patrol, Docker helper guard, and H100 vLLM smoke",+ ]+ for marker in required_markers:+ assert marker in text++ assert "[ ] Record concise terminal outputs for release notes" not in text