| | |
|---|
| | | python asr recognizer lib
|
|---|
| | |
|
|---|
| | | '''
|
|---|
| | | def __init__(self, host="127.0.0.1", port="30035", is_ssl=True,chunk_size="5, 10, 5",chunk_interval=10,mode="offline",wav_name="default"):
|
|---|
| | | def __init__(self, host="127.0.0.1",
|
|---|
| | | port="30035",
|
|---|
| | | is_ssl=True,
|
|---|
| | | chunk_size="0, 10, 5",
|
|---|
| | | chunk_interval=10,
|
|---|
| | | mode="offline",
|
|---|
| | | wav_name="default"):
|
|---|
| | | '''
|
|---|
| | | host: server host ip
|
|---|
| | | port: server port
|
|---|
| | |
|---|
| | | stride = int(60 * chunk_size[1]/ chunk_interval / 1000 * 16000 * 2)
|
|---|
| | | chunk_num = (len(audio_bytes) - 1) // stride + 1
|
|---|
| | |
|
|---|
| | | message = json.dumps({"mode": args.mode, "chunk_size": args.chunk_size, "encoder_chunk_look_back": 4,
|
|---|
| | | "decoder_chunk_look_back": 1, "chunk_interval": args.chunk_interval, |
|---|
| | | "wav_name": wav_name, "is_speaking": True})
|
|---|
| | | message = json.dumps({"mode": mode,
|
|---|
| | | "chunk_size": chunk_size,
|
|---|
| | | "encoder_chunk_look_back": 4,
|
|---|
| | | "decoder_chunk_look_back": 1,
|
|---|
| | | "chunk_interval": chunk_interval,
|
|---|
| | | "wav_name": wav_name,
|
|---|
| | | "is_speaking": True})
|
|---|
| | |
|
|---|
| | | self.websocket.send(message)
|
|---|
| | |
|
|---|
| | |
|---|
| | | return msg
|
|---|
| | | except:
|
|---|
| | | return ""
|
|---|
| | | |
|---|
| | | def close(self,timeout=1):
|
|---|
| | | message = json.dumps({"is_speaking": False})
|
|---|
| | | self.websocket.send(message)
|
|---|
| | |
|---|
| | | return msg
|
|---|
| | |
|
|---|
| | | if __name__ == '__main__':
|
|---|
| | | |
|---|
| | | print('example for Funasr_websocket_recognizer')
|
|---|
| | | import wave
|
|---|
| | | wav_path="asr_example.wav"
|
|---|
| | | wav_path = "/Users/zhifu/Downloads/modelscope_models/speech_seaco_paraformer_large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/example/asr_example.wav"
|
|---|
| | | with wave.open(wav_path, "rb") as wav_file:
|
|---|
| | | params = wav_file.getparams()
|
|---|
| | | frames = wav_file.readframes(wav_file.getnframes())
|
|---|
| | |
|---|
| | | stride = int(60 * 10 / 10 / 1000 * 16000 * 2)
|
|---|
| | | chunk_num = (len(audio_bytes) - 1) // stride + 1
|
|---|
| | | # create an recognizer
|
|---|
| | | rcg=Funasr_websocket_recognizer(host="127.0.0.1",port="30035",is_ssl=True,mode="2pass")
|
|---|
| | | rcg = Funasr_websocket_recognizer(host="127.0.0.1",
|
|---|
| | | port="10095",
|
|---|
| | | is_ssl=True,
|
|---|
| | | mode="2pass",
|
|---|
| | | chunk_size="0,10,5")
|
|---|
| | | # loop to send chunk
|
|---|
| | | for i in range(chunk_num):
|
|---|
| | |
|
|---|
