Text and audio very long

Support & Feedback Forum
1

I want to import a text which has in my word document 130 pages. I also have an MP3 audio file for the text.

I imported the whole word document. LingQ split the text in three parts, but they are all really long. Also the MP3 file is too large.

  1. If I import a long text, can I influence in how many parts the text is split? - I assume, I could just make several word files and import each individually, but I am wondering whether there are other options.

  2. Can someone recommend a programme to cut an MP3 in several parts. My file is almost 300 MB. I should therefore probably split the file in at least 5 parts.

2

I imported the whole word document. LingQ split the text in three parts, but they are all really long. Also the MP3 file is too large.

The lessons can only be so long you are correct, and the splitting only happens after a lesson becomes full.

Can someone recommend a programme to cut an MP3 in several parts. My file is almost 300 MB. I should therefore probably split the file in at least 5 parts.

Here’s a python script to split your audio files into 5 parts

#Install these dependencies 
pip install pydub
apt-get install ffmpeg

from pydub import AudioSegment

def split_mp3(input_file, output_folder, parts=5):
    # Load the mp3 file
    audio = AudioSegment.from_mp3(input_file)

    # Calculate the length of each part
    length = len(audio) // parts

    # Split the mp3 file and save each part
    for i in range(parts):
        part = audio[i * length: (i + 1) * length if i != parts - 1 else len(audio)]
        part_path = f"{output_folder}/part_{i + 1}.mp3"
        part.export(part_path, format="mp3")
        print(f"Saved part {i + 1} as {part_path}")

input_file = "path/to/yourfile.mp3"  # Provide the path to the MP3 file you want to split
output_folder = "path/to/output"     # Provide the folder where you want to save the split parts
split_mp3(input_file, output_folder)

You could add a way to split the text at the same point but that would require some sort of timestamp information. You could run a speech to text generation model on your computer and have it timestamp your file.

Buzz is a great free customizable tool for this purpose

With that information you could enhance that python script to cut the text at the same time.

Good luck!

3

Thank you for your detailed explanations. I am not sure whether my computer skills are sufficient for this, but I will have a closer look at the suggestions.
I had another look at my word document and I think, I will decide at which points splits make sense and split the text in 5 - 6 parts, then I deal with the audio file.
I am sure it will take quite some time to have the lessons in proper from, but at the moment the text is quite difficult anyway.
If anyone else has any other ideas, then feel free to comment.

4

You can split the mp3 using the program audacity for example. It’s freeware.

4 Likes