Skip to content

Open-source speech recognition toolkit for training, inference, streaming ASR, VAD, punctuation, speaker diarization pipelines, and OpenAI-compatible/MCP serving.

Fix audio format 2.0 (#2186)

Djraemon7e9696f15635
diff --git a/runtime/python/onnxruntime/demo_paraformer_online.py b/runtime/python/onnxruntime/demo_paraformer_online.py
index bb72b41a1..cca5357ab 100644
--- a/runtime/python/onnxruntime/demo_paraformer_online.py
+++ b/runtime/python/onnxruntime/demo_paraformer_online.py
@@ -3,7 +3,8 @@ from funasr_onnx.paraformer_online_bin import Paraformer
from pathlib import Path
model_dir = "damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-online"
-wav_path = ["{}/.cache/modelscope/hub/{}/example/asr_example.wav".format(Path.home(), model_dir)]
+#wav_path = ["{}/.cache/modelscope/hub/{}/example/asr_example.wav".format(Path.home(), model_dir)]
+wav_path = "{}/.cache/modelscope/hub/{}/example/asr_example.wav".format(Path.home(), model_dir)
chunk_size = [5, 10, 5]
model = Paraformer(
diff --git a/runtime/python/onnxruntime/funasr_onnx/paraformer_bin.py b/runtime/python/onnxruntime/funasr_onnx/paraformer_bin.py
index 4f35fcc86..bde7f442e 100644
--- a/runtime/python/onnxruntime/funasr_onnx/paraformer_bin.py
+++ b/runtime/python/onnxruntime/funasr_onnx/paraformer_bin.py
@@ -175,7 +175,23 @@ class Paraformer:
plt.savefig(plotname, bbox_inches="tight")
def load_data(self, wav_content: Union[str, np.ndarray, List[str]], fs: int = None) -> List:
+ def convert_to_wav(input_path, output_path):
+ from pydub import AudioSegment
+ try:
+ audio = AudioSegment.from_mp3(input_path)
+ audio.export(output_path, format="wav")
+ print("音频文件为mp3格式,已转换为wav格式")
+
+ except Exception as e:
+ print(f"转换失败:{e}")
+
def load_wav(path: str) -> np.ndarray:
+ if not path.lower().endswith('.wav'):
+ import os
+ input_path = path
+ path = os.path.splitext(path)[0]+'.wav'
+ convert_to_wav(input_path,path) #将mp3格式转换成wav格式
+
waveform, _ = librosa.load(path, sr=fs)
return waveform
diff --git a/runtime/python/onnxruntime/funasr_onnx/paraformer_online_bin.py b/runtime/python/onnxruntime/funasr_onnx/paraformer_online_bin.py
index ddd857d37..3f63ea020 100644
--- a/runtime/python/onnxruntime/funasr_onnx/paraformer_online_bin.py
+++ b/runtime/python/onnxruntime/funasr_onnx/paraformer_online_bin.py
@@ -208,7 +208,24 @@ class Paraformer:
return asr_res
def load_data(self, wav_content: Union[str, np.ndarray, List[str]], fs: int = None) -> List:
+
+ def convert_to_wav(input_path, output_path):
+ from pydub import AudioSegment
+ try:
+ audio = AudioSegment.from_mp3(input_path)
+ audio.export(output_path, format="wav")
+ print("音频文件为mp3格式,已转换为wav格式")
+
+ except Exception as e:
+ print(f"转换失败:{e}")
+
def load_wav(path: str) -> np.ndarray:
+ if not path.lower().endswith('.wav'):
+ import os
+ input_path = path
+ path = os.path.splitext(path)[0]+'.wav'
+ convert_to_wav(input_path,path) #将mp3格式转换成wav格式
+
waveform, _ = librosa.load(path, sr=fs)
return waveform
diff --git a/runtime/python/onnxruntime/funasr_onnx/vad_bin.py b/runtime/python/onnxruntime/funasr_onnx/vad_bin.py
index 92928a840..3f21004bf 100644
--- a/runtime/python/onnxruntime/funasr_onnx/vad_bin.py
+++ b/runtime/python/onnxruntime/funasr_onnx/vad_bin.py
@@ -143,7 +143,24 @@ class Fsmn_vad:
return segments
def load_data(self, wav_content: Union[str, np.ndarray, List[str]], fs: int = None) -> List:
+
+ def convert_to_wav(input_path, output_path):
+ from pydub import AudioSegment
+ try:
+ audio = AudioSegment.from_mp3(input_path)
+ audio.export(output_path, format="wav")
+ print("音频文件为mp3格式,已转换为wav格式")
+
+ except Exception as e:
+ print(f"转换失败:{e}")
+
def load_wav(path: str) -> np.ndarray:
+ if not path.lower().endswith('.wav'):
+ import os
+ input_path = path
+ path = os.path.splitext(path)[0]+'.wav'
+ convert_to_wav(input_path,path) #将mp3格式转换成wav格式
+
waveform, _ = librosa.load(path, sr=fs)
return waveform