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
Update funasr_wss_server.py (#1322)
dudulu6cdbcf4b0aac
diff --git a/runtime/python/websocket/funasr_wss_server.py b/runtime/python/websocket/funasr_wss_server.pyindex fa82ea525..513a2f62b 100644--- a/runtime/python/websocket/funasr_wss_server.py+++ b/runtime/python/websocket/funasr_wss_server.py@@ -179,7 +179,8 @@ async def ws_serve(websocket, path):if "wav_name" in messagejson:websocket.wav_name = messagejson.get("wav_name")if "chunk_size" in messagejson:- websocket.status_dict_asr_online["chunk_size"] = messagejson["chunk_size"]+ chunk_size = messagejson["chunk_size"].split(',')+ websocket.status_dict_asr_online["chunk_size"] = [int(x) for x in chunk_size]if "encoder_chunk_look_back" in messagejson:websocket.status_dict_asr_online["encoder_chunk_look_back"] = messagejson["encoder_chunk_look_back"]if "decoder_chunk_look_back" in messagejson: