Fix audio format 2.0 (#2186)

Djraemon

2024-11-04 7e9696f15635a83ff810cc86b79c0932cb4c8a27

Fix audio format 2.0 (#2186)

* 添加了对音频文件扩展名是否为.mp3的补丁，是mp3格式则转化为wav格式

* 增加检测音频文件是否为mp3格式的补丁

* 完善对音频文件后缀名的检查，若文件后缀不是.wav，则转化为wav

* 增加音频文件后缀名检查；音频文件无效时抛出错误

* 在paraformer、vad两个模型中加入对音频文件后缀的检查，并将非wav格式转为wav格式

* 修改wav_path的数据类型，使demo能够顺利运行

 runtime/python/onnxruntime/demo_paraformer_online.py

@@ -3,7 +3,8 @@
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(

 runtime/python/onnxruntime/funasr_onnx/paraformer_bin.py

@@ -175,7 +175,23 @@
        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


 runtime/python/onnxruntime/funasr_onnx/paraformer_online_bin.py

@@ -208,7 +208,24 @@
        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


 runtime/python/onnxruntime/funasr_onnx/vad_bin.py

@@ -143,7 +143,24 @@
        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