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
pcm unfix
游雁4b3a28cbc5fd
diff --git a/funasr/utils/load_utils.py b/funasr/utils/load_utils.pyindex aabf5d9f3..9613d1b39 100644--- a/funasr/utils/load_utils.py+++ b/funasr/utils/load_utils.py@@ -138,7 +138,7 @@ def load_audio_text_image_video(def load_bytes(input):- input = validate_frame_rate(input)+ # input = validate_frame_rate(input)middle_data = np.frombuffer(input, dtype=np.int16)middle_data = np.asarray(middle_data)if middle_data.dtype.kind not in "iu":@@ -153,11 +153,12 @@ def load_bytes(input):array = np.frombuffer((middle_data.astype(dtype) - offset) / abs_max, dtype=np.float32)return array+def validate_frame_rate(input,fs: int = 16000,):-+# 将文件读取为字节流byte_data = BytesIO(input)@@ -175,7 +176,7 @@ def validate_frame_rate(# 获取重新采样后的字节流数据input = output.read()-+return input