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
atsr
语帆d4955ba39594
diff --git a/funasr/utils/load_utils.py b/funasr/utils/load_utils.pyindex 87412bd87..ccb5670c2 100644--- a/funasr/utils/load_utils.py+++ b/funasr/utils/load_utils.py@@ -31,6 +31,7 @@ def load_audio_text_image_video(data_or_path_or_list, fs: int = 16000, audio_fs:return [load_audio_text_image_video(audio, fs=fs, audio_fs=audio_fs, data_type=data_type, **kwargs) for audio in data_or_path_or_list]if isinstance(data_or_path_or_list, str) and data_or_path_or_list.startswith('http'): # download url to local filedata_or_path_or_list = download_from_url(data_or_path_or_list)+ pdb.set_trace()if isinstance(data_or_path_or_list, str) and os.path.exists(data_or_path_or_list): # local fileif data_type is None or data_type == "sound":data_or_path_or_list, audio_fs = torchaudio.load(data_or_path_or_list)@@ -66,7 +67,7 @@ def load_audio_text_image_video(data_or_path_or_list, fs: int = 16000, audio_fs:else:pass# print(f"unsupport data type: {data_or_path_or_list}, return raw data")-+ pdb.set_trace()if audio_fs != fs and data_type != "text":resampler = torchaudio.transforms.Resample(audio_fs, fs)data_or_path_or_list = resampler(data_or_path_or_list[None, :])[0, :]