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 demo.py
zhifu gaof921a7181855
diff --git a/examples/industrial_data_pretraining/sense_voice/demo.py b/examples/industrial_data_pretraining/sense_voice/demo.pyindex 642e82501..7a15cf2c8 100644--- a/examples/industrial_data_pretraining/sense_voice/demo.py+++ b/examples/industrial_data_pretraining/sense_voice/demo.py@@ -20,7 +20,7 @@ model = AutoModel(res = model.generate(input=f"{model.model_path}/example/en.mp3",cache={},- language="auto", # "zn", "en", "yue", "ja", "ko", "nospeech"+ language="auto", # "zh", "en", "yue", "ja", "ko", "nospeech"use_itn=True,batch_size_s=60,merge_vad=True, #@@ -33,7 +33,7 @@ print(text)res = model.generate(input=f"{model.model_path}/example/en.mp3",cache={},- language="auto", # "zn", "en", "yue", "ja", "ko", "nospeech"+ language="auto", # "zh", "en", "yue", "ja", "ko", "nospeech"use_itn=True,batch_size_s=60,merge_vad=True, #@@ -48,7 +48,7 @@ print(text)res = model.generate(input=f"{model.model_path}/example/zh.mp3",cache={},- language="auto", # "zn", "en", "yue", "ja", "ko", "nospeech"+ language="auto", # "zh", "en", "yue", "ja", "ko", "nospeech"use_itn=True,batch_size_s=60,merge_vad=True, #@@ -61,7 +61,7 @@ print(text)res = model.generate(input=f"{model.model_path}/example/zh.mp3",cache={},- language="auto", # "zn", "en", "yue", "ja", "ko", "nospeech"+ language="auto", # "zh", "en", "yue", "ja", "ko", "nospeech"use_itn=True,batch_size_s=60,merge_vad=True, #@@ -76,7 +76,7 @@ print(text)res = model.generate(input=f"{model.model_path}/example/yue.mp3",cache={},- language="auto", # "zn", "en", "yue", "ja", "ko", "nospeech"+ language="auto", # "zh", "en", "yue", "ja", "ko", "nospeech"use_itn=True,batch_size_s=60,merge_vad=True, #@@ -89,7 +89,7 @@ print(text)res = model.generate(input=f"{model.model_path}/example/ja.mp3",cache={},- language="auto", # "zn", "en", "yue", "ja", "ko", "nospeech"+ language="auto", # "zh", "en", "yue", "ja", "ko", "nospeech"use_itn=True,batch_size_s=60,merge_vad=True, #@@ -103,7 +103,7 @@ print(text)res = model.generate(input=f"{model.model_path}/example/ko.mp3",cache={},- language="auto", # "zn", "en", "yue", "ja", "ko", "nospeech"+ language="auto", # "zh", "en", "yue", "ja", "ko", "nospeech"use_itn=True,batch_size_s=60,merge_vad=True, #