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
ffmpeg
游雁3d73f50beb39
diff --git a/funasr/utils/load_utils.py b/funasr/utils/load_utils.pyindex b3fc2be83..484940874 100644--- a/funasr/utils/load_utils.py+++ b/funasr/utils/load_utils.py@@ -28,9 +28,9 @@ def is_ffmpeg_installed():use_ffmpeg=Falseif is_ffmpeg_installed():- use_ffmpeg+ use_ffmpeg = Trueelse:- print("Warning: ffmpeg is not installed. torchaudio is used to load audio")+ print("Notice: ffmpeg is not installed. torchaudio is used to load audio")def load_audio_text_image_video(data_or_path_or_list, fs: int = 16000, audio_fs: int = 16000, data_type="sound", tokenizer=None, **kwargs):if isinstance(data_or_path_or_list, (list, tuple)):