funasr

from funasr import AutoModel import soundfile as sf import os # You might need to set an environment variable for modelscope token if hitting rate limits or private models # os.environ['MODELSCOPE_API_TOKEN'] = 'your_token_here' # Initialize the ASR model, will download 'paraformer-zh' from ModelScope if not local # 'paraformer-zh' is a multi-functional model, with VAD and PUNC integrated. # Use a public audio URL for demonstration model = AutoModel(model="paraformer-zh", vad_model="fsmn-vad", punc_model="ct-punc-c", device="cpu") # Specify 'cuda:0' for GPU if available # Example audio input: a remote URL or a local file path # For a local file, ensure it exists, e.g., 'path/to/your/audio.wav' # Using a provided example audio from FunASR's repository audio_input = "https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/vad_example.wav" print(f"Processing audio: {audio_input}") # Perform speech recognition # The generate method returns a list of dictionaries with transcription results result = model.generate(input=audio_input) # Print the transcription result if result and result[0].get('text'): print(f"Transcription: {result[0]['text']}") else: print("No transcription result found.") # Example of VAD (Voice Activity Detection) # model_vad = AutoModel(model="fsmn-vad", device="cpu") # vad_result = model_vad.generate(input=audio_input) # print(f"VAD Result: {vad_result}")