Skip to content

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

docs: fix README streaming example (runnable + actually streams) (#2987)

zhifu gao7e01e9440c14
diff --git a/README.md b/README.md
index 0b200c6a0..944d7ad4d 100644
--- a/README.md
+++ b/README.md
@@ -191,9 +191,20 @@ model = AutoModel(model="FunAudioLLM/Fun-ASR-Nano-2512", hub="hf", trust_remote_
vad_model="fsmn-vad", vad_kwargs={"max_single_segment_time": 30000}, device="cuda")
result = model.generate(input="audio.wav", batch_size=1)
-# Streaming real-time
+# Streaming real-time (feed audio chunk by chunk)
+import soundfile as sf
model = AutoModel(model="paraformer-zh-streaming", device="cuda")
-result = model.generate(input="chunk.wav", cache={}, chunk_size=[0, 10, 5])
+audio, sr = sf.read("speech.wav", dtype="float32") # 16 kHz mono
+chunk_size = [0, 10, 5] # 600 ms chunks
+chunk_stride = chunk_size[1] * 960
+cache = {}
+n_chunks = (len(audio) - 1) // chunk_stride + 1
+for i in range(n_chunks):
+ chunk = audio[i * chunk_stride : (i + 1) * chunk_stride]
+ res = model.generate(input=chunk, cache=cache, is_final=(i == n_chunks - 1),
+ chunk_size=chunk_size, encoder_chunk_look_back=4, decoder_chunk_look_back=1)
+ if res[0]["text"]:
+ print(res[0]["text"], end="", flush=True)
# Emotion recognition
model = AutoModel(model="emotion2vec_plus_large", device="cuda")
diff --git a/README_zh.md b/README_zh.md
index 505c30206..13471206f 100644
--- a/README_zh.md
+++ b/README_zh.md
@@ -189,9 +189,20 @@ model = AutoModel(model="FunAudioLLM/Fun-ASR-Nano-2512", hub="hf", trust_remote_
vad_model="fsmn-vad", vad_kwargs={"max_single_segment_time": 30000}, device="cuda")
result = model.generate(input="audio.wav", batch_size=1)
-# 流式实时识别
+# 流式实时识别(逐块喂音频)
+import soundfile as sf
model = AutoModel(model="paraformer-zh-streaming", device="cuda")
-result = model.generate(input="chunk.wav", cache={}, chunk_size=[0, 10, 5])
+audio, sr = sf.read("speech.wav", dtype="float32") # 16 kHz 单声道
+chunk_size = [0, 10, 5] # 每块 600ms
+chunk_stride = chunk_size[1] * 960
+cache = {}
+n_chunks = (len(audio) - 1) // chunk_stride + 1
+for i in range(n_chunks):
+ chunk = audio[i * chunk_stride : (i + 1) * chunk_stride]
+ res = model.generate(input=chunk, cache=cache, is_final=(i == n_chunks - 1),
+ chunk_size=chunk_size, encoder_chunk_look_back=4, decoder_chunk_look_back=1)
+ if res[0]["text"]:
+ print(res[0]["text"], end="", flush=True)
# 情感识别
model = AutoModel(model="emotion2vec_plus_large", device="cuda")