将 mp3 转录为文本（python）-->“RIFF id”错误

Question

我正在尝试将 mp3 文件转换为文本，但我的代码返回了下面列出的错误。任何帮助表示赞赏！

这是一个示例 mp3 文件。以下是我尝试过的：

import speech_recognition as sr
print(sr.__version__)
r = sr.Recognizer()

file_audio = sr.AudioFile(r"C:\Users\Andrew\Podcast.mp3")

with file_audio as source:
    audio_text = r.record(source)

print(type(audio_text))
print(r.recognize_google(audio_text))

我得到的完整

error。似乎是：

Error: file does not start with RIFF id 感谢您的帮助！

Answer 1

你需要先把mp3转成wav，然后你就可以转录了，下面是你的代码修改后的版本。

import speech_recognition as sr
from pydub import AudioSegment

# convert mp3 file to wav  
src=(r"C:\Users\Andrew\Podcast.mp3")
sound = AudioSegment.from_mp3(src)
sound.export("C:\Users\Andrew\podcast.wav", format="wav")

file_audio = sr.AudioFile(r"C:\Users\Andrew\Podcast.wav")

# use the audio file as the audio source                                        
r = sr.Recognizer()
with file_audio as source:
audio_text = r.record(source)

print(type(audio_text))
print(r.recognize_google(audio_text))

在上面的修改代码中，首先将mp3文件转换为wav，然后进行转录过程。

Answer 2

您可以做的一件事是将 mp3 转换为 wav。使用 mp3 文件进行测试时，我遇到了与您相同的错误。但转换后，您的代码运行良好。也可以编写您的代码，以便您可以使用 mp3，但我的知识到此为止。

也许其他人比我知道的更多，而不是他发布的。但如果你只是想测试，你现在可以使用 audacity 之类的东西来转换它。

如果您使用大文件，您也可能会遇到问题，请在线阅读有关此的内容。但是没有什么能阻止你尝试。

这是相关网站：

https://www.geeksforgeeks.org/python-speech-recognition-on-large-audio-files/

Answer 3

import speech_recognition as sr
import os
from pydub import AudioSegment
from pydub.silence import split_on_silence

# Create a speech recognition object
recognizer = sr.Recognizer()

def transcribe_large_audio_file(audio_path):
    """Split audio into chunks and apply speech recognition"""
    # Load audio file with pydub
    audio = AudioSegment.from_mp3(audio_path)
    # Split audio at silent parts with duration of 700ms or more and obtain chunks
    audio_chunks = split_on_silence(audio, min_silence_len=700, silence_thresh=audio.dBFS-14, keep_silence=700)

    # Create a directory to store audio chunks
    chunks_dir = "audio-chunks"
    if not os.path.isdir(chunks_dir):
        os.mkdir(chunks_dir)

    full_text = ""
    failed_attempts = 0
    # Process each audio chunk
    for i, chunk in enumerate(audio_chunks, start=1):
        # Save chunk in the directory
        chunk_file_name = os.path.join(chunks_dir, f"chunk{i}.wav")
        chunk.export(chunk_file_name, format="wav")
        # Recognize audio from the chunk
        with sr.WavFile(chunk_file_name) as src:
            listened_audio = recognizer.listen(src)
            # Convert audio to text
            try:
                text = recognizer.recognize(listened_audio)
            except:
                failed_attempts += 1
                if failed_attempts == 5:
                    print(f"Skipping {audio_path} due to too many errors")
                    break
            else:
                failed_attempts = 0
                text = f"{text.capitalize()}. "
                print(chunk_file_name, ":", text)
                full_text += text
    # Return the transcription for all chunks
    return full_text

output_dir = "C:\\Store\\output"
os.makedirs(output_dir, exist_ok=True)
processed_files = []

# Iterate through all .mp3 files in the directory
with open(os.path.join(output_dir, 'result.txt'), 'w') as result_file:
    for file in os.listdir(output_dir):
        if file.endswith(".mp3") and file not in processed_files:
            mp3_file_path = os.path.join(output_dir, file)
            print(f"Processing {mp3_file_path}")
            try:
                transcription = transcribe_large_audio_file(mp3_file_path)
            except LookupError as error:
                print(f"Skipping {mp3_file_path} due to error: {error}")
                continue
            else:
                print(transcription)
                # Save the transcription to a file with the same name as the audio file
                txt_file_path = os.path.join(output_dir, f"{os.path.splitext(file)[0]}.txt")
                with open(txt_file_path, 'w') as txt_file:
                    txt_file.write(transcription)
                print(f"Transcription saved to {txt_file_path}")
                print(transcription, file=result_file)
                processed_files.append(file)