Skip to content

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

docs(README): make the quickstart runnable (add missing model.generate() call + CPU note) (#3010)

zhifu gaob0ef72a92ad0
diff --git a/README.md b/README.md
index 03af1681c..d8efff4b0 100644
--- a/README.md
+++ b/README.md
@@ -41,9 +41,14 @@ pip install funasr
from funasr import AutoModel
from funasr.utils.postprocess_utils import rich_transcription_postprocess
-model = AutoModel(model="iic/SenseVoiceSmall", vad_model="fsmn-vad", spk_model="cam++", device="cuda")
+model = AutoModel(model="iic/SenseVoiceSmall", vad_model="fsmn-vad", spk_model="cam++", device="cuda") # use device="cpu" if you don't have a GPU
result = model.generate(input="https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_zh.wav")
+result = model.generate(
+ input="https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_zh.wav",
+ batch_size_s=300,
+)
+
# 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'])}")