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
qwenaudio qwenaudiochat
游雁9c2ff37ae990
diff --git a/examples/industrial_data_pretraining/qwen_audio/demo.py b/examples/industrial_data_pretraining/qwen_audio/demo.pyindex 6ec4ea5f8..41bbb9977 100644--- a/examples/industrial_data_pretraining/qwen_audio/demo.py+++ b/examples/industrial_data_pretraining/qwen_audio/demo.py@@ -7,9 +7,7 @@from funasr import AutoModel-model = AutoModel(model="Qwen-Audio",- model_path=None,- )+model = AutoModel(model="Qwen-Audio")res = model.generate(input="https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_zh.wav", language=None)print(res)diff --git a/examples/industrial_data_pretraining/qwen_audio/demo_chat.py b/examples/industrial_data_pretraining/qwen_audio/demo_chat.pyindex e8c6cf49e..a2fb05be0 100644--- a/examples/industrial_data_pretraining/qwen_audio/demo_chat.py+++ b/examples/industrial_data_pretraining/qwen_audio/demo_chat.py@@ -7,9 +7,7 @@from funasr import AutoModel-model = AutoModel(model="Qwen-Audio-Chat",- model_path=None,- )+model = AutoModel(model="Qwen-Audio-Chat")audio_in = "https://github.com/QwenLM/Qwen-Audio/raw/main/assets/audio/1272-128104-0000.flac"@@ -19,8 +17,9 @@ cache = {"history": None}res = model.generate(input=audio_in, prompt=prompt, cache=cache)print(res)-prompt = 'Find the start time and end time of the word "middle classes"'+# 2nd dialogue turn+prompt = 'Find the start time and end time of the word "middle classes"'res = model.generate(input=None, prompt=prompt, cache=cache)print(res)diff --git a/examples/industrial_data_pretraining/qwen_audio/demo_chat_from_local.py b/examples/industrial_data_pretraining/qwen_audio/demo_chat_from_local.pyindex d3c19b261..233321765 100644--- a/examples/industrial_data_pretraining/qwen_audio/demo_chat_from_local.py+++ b/examples/industrial_data_pretraining/qwen_audio/demo_chat_from_local.py@@ -19,8 +19,9 @@ cache = {"history": None}res = model.generate(input=audio_in, prompt=prompt, cache=cache)print(res)-prompt = 'Find the start time and end time of the word "middle classes"'+# 2nd dialogue turn+prompt = 'Find the start time and end time of the word "middle classes"'res = model.generate(input=None, prompt=prompt, cache=cache)print(res)