add

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+example/asr_example.wav filter=lfs diff=lfs merge=lfs -text

README.md

@@ -100,28 +100,31 @@ print(res)
 Note: `model_hub`: represents the model repository, `ms` stands for selecting ModelScope download, `hf` stands for selecting Huggingface download.
 
 ### Speech Recognition (Streaming)
+
 ```python
 from funasr import AutoModel
 
-chunk_size = [0, 10, 5] #[0, 10, 5] 600ms, [0, 8, 4] 480ms
-encoder_chunk_look_back = 4 #number of chunks to lookback for encoder self-attention
-decoder_chunk_look_back = 1 #number of encoder chunks to lookback for decoder cross-attention
+chunk_size = [0, 10, 5]  # [0, 10, 5] 600ms, [0, 8, 4] 480ms
+encoder_chunk_look_back = 4  # number of chunks to lookback for encoder self-attention
+decoder_chunk_look_back = 1  # number of encoder chunks to lookback for decoder cross-attention
 
 model = AutoModel(model="paraformer-zh-streaming", model_revision="v2.0.4")
 
 import soundfile
 import os
 
-wav_file = os.path.join(model.model_path, "example/asr_example.wav")
+wav_file = os.path.join(model.model_path, "../fa-zh/example/asr_example.wav")
 speech, sample_rate = soundfile.read(wav_file)
-chunk_stride = chunk_size[1] * 960 # 600ms
+chunk_stride = chunk_size[1] * 960  # 600ms
 
 cache = {}
-total_chunk_num = int(len((speech)-1)/chunk_stride+1)
+total_chunk_num = int(len((speech) - 1) / chunk_stride + 1)
 for i in range(total_chunk_num):
-    speech_chunk = speech[i*chunk_stride:(i+1)*chunk_stride]
+    speech_chunk = speech[i * chunk_stride:(i + 1) * chunk_stride]
     is_final = i == total_chunk_num - 1
-    res = model.generate(input=speech_chunk, cache=cache, is_final=is_final, chunk_size=chunk_size, encoder_chunk_look_back=encoder_chunk_look_back, decoder_chunk_look_back=decoder_chunk_look_back)
+    res = model.generate(input=speech_chunk, cache=cache, is_final=is_final, chunk_size=chunk_size,
+                         encoder_chunk_look_back=encoder_chunk_look_back,
+                         decoder_chunk_look_back=decoder_chunk_look_back)
     print(res)
 ```
 Note: `chunk_size` is the configuration for streaming latency.` [0,10,5]` indicates that the real-time display granularity is `10*60=600ms`, and the lookahead information is `5*60=300ms`. Each inference input is `600ms` (sample points are `16000*0.6=960`), and the output is the corresponding text. For the last speech segment input, `is_final=True` needs to be set to force the output of the last word.

example/asr_example.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:732f28a4445eb2b656675b946695e59752b7df824d475c4bc531c441f43b30f9
+size 417742