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
docs: make README quickstart runnable and output truthful (#2986)
zhifu gao82a1245c8014
diff --git a/README.md b/README.mdindex 7f7981b91..0b200c6a0 100644--- a/README.md+++ b/README.md@@ -39,16 +39,19 @@ pip install funasr```pythonfrom funasr import AutoModel+from funasr.utils.postprocess_utils import rich_transcription_postprocessmodel = AutoModel(model="iic/SenseVoiceSmall", vad_model="fsmn-vad", spk_model="cam++", device="cuda")-result = model.generate(input="meeting.wav")+result = model.generate(input="https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_zh.wav")++# One call returns VAD segments with speaker id + timestamps — render them however you like:+for seg in result[0]["sentence_info"]:+ print(f"[{seg['start']/1000:.1f}s] Speaker {seg['spk']}: {rich_transcription_postprocess(seg['sentence'])}")```**Output** — structured text with speaker labels, timestamps, and punctuation:```-[00:00.4 → 00:03.8] Speaker 0: Let's discuss the Q3 plan.-[00:04.2 → 00:07.1] Speaker 1: Sounds good. I have three points.-[00:07.5 → 00:12.3] Speaker 0: Go ahead. We have 30 minutes.+[0.6s] Speaker 0: 欢迎大家来体验达摩院推出的语音识别模型```That's it. **One model, one call** — VAD segmentation, speech recognition, punctuation, speaker diarization all happen automatically.@@ -61,7 +64,7 @@ For highest accuracy across 31 languages (including Chinese dialects), use [Fun-from funasr import AutoModelmodel = AutoModel(model="FunAudioLLM/Fun-ASR-Nano-2512", vad_model="fsmn-vad", device="cuda")-result = model.generate(input="meeting.wav")+result = model.generate(input="https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_zh.wav")```With vLLM acceleration (16x faster, batch processing):@@ -181,7 +184,7 @@ from funasr import AutoModel# Chinese production (VAD + ASR + punctuation + speaker)model = AutoModel(model="paraformer-zh", vad_model="fsmn-vad", punc_model="ct-punc", spk_model="cam++", device="cuda")-result = model.generate(input="meeting.wav", hotword="关键词 20")+result = model.generate(input="https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_zh.wav", hotword="关键词 20")# 31 languages with timestampsmodel = AutoModel(model="FunAudioLLM/Fun-ASR-Nano-2512", hub="hf", trust_remote_code=True,diff --git a/README_zh.md b/README_zh.mdindex bab10b386..505c30206 100644--- a/README_zh.md+++ b/README_zh.md@@ -38,16 +38,19 @@ pip install funasr```pythonfrom funasr import AutoModel+from funasr.utils.postprocess_utils import rich_transcription_postprocessmodel = AutoModel(model="iic/SenseVoiceSmall", vad_model="fsmn-vad", spk_model="cam++", device="cuda")-result = model.generate(input="meeting.wav")+result = model.generate(input="https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_zh.wav")++# 一次调用即返回带说话人 id 和时间戳的 VAD 分段,可自由渲染:+for seg in result[0]["sentence_info"]:+ print(f"[{seg['start']/1000:.1f}s] 说话人{seg['spk']}: {rich_transcription_postprocess(seg['sentence'])}")```**输出** — 带说话人标签、时间戳和标点的结构化文本:```-[00:00.4 → 00:03.8] 说话人0: 我们今天讨论一下 Q3 的计划。-[00:04.2 → 00:07.1] 说话人1: 好的,我有三个要点。-[00:07.5 → 00:12.3] 说话人0: 请讲,我们还有 30 分钟。+[0.6s] 说话人0: 欢迎大家来体验达摩院推出的语音识别模型```一个模型、一次调用 — VAD 分段、语音识别、标点恢复、说话人分离全部自动完成。@@ -60,7 +63,7 @@ result = model.generate(input="meeting.wav")from funasr import AutoModelmodel = AutoModel(model="FunAudioLLM/Fun-ASR-Nano-2512", vad_model="fsmn-vad", device="cuda")-result = model.generate(input="meeting.wav")+result = model.generate(input="https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_zh.wav")```使用 vLLM 加速(批量处理快 16 倍):@@ -179,7 +182,7 @@ from funasr import AutoModel# 中文生产级(VAD + 识别 + 标点 + 说话人)model = AutoModel(model="paraformer-zh", vad_model="fsmn-vad", punc_model="ct-punc", spk_model="cam++", device="cuda")-result = model.generate(input="meeting.wav", hotword="关键词 20")+result = model.generate(input="https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_zh.wav", hotword="关键词 20")# 31 种语言 + 时间戳model = AutoModel(model="FunAudioLLM/Fun-ASR-Nano-2512", hub="hf", trust_remote_code=True,