I want to ask about whisper ai

[cns00]

I have some questions about whisper ai.

I am following https://www.youtube.com/watch?v=ABFqbY_rmEk to install whisper ai. I have Windows 11 on my laptop.

I did the 5 steps in the video. Assume that the audio file is test.wav. I said:
whisper test.wav

It is downloading large-v3-turbo.pt since this is the first time that I ran the command. It is 1.5gb. The problem is that my internet is horrible. The download is failing. It reached 18% and then the download fails and I get an error message that says:
RuntimeError: Model has been downloaded but the SHA256 checksum does not not match. Please retry loading the model.

I tried it again. It reached 34% and failed. I tried it again. It reached 55% and failed. I even tested it by using a VPN and still no luck. In the end the download got stuck on say 34% and it's not proceeding. The download got stuck 3 times.

I saw #1027. They said that the issue was fixed if you deleted:
"C:\Users.cache\torch\whisperx-vad-segmentation.bin"
"C:\Users\USER-NAME.cache\torch\whisperx-vad-segmentation.bak"

I don't have those files. What do I do? How do I download large-v3-turbo.pt?

I have subtitle files for the non English parts of my movies in which lines show before\after a person starts speaking and they go away before\after a person stops speaking and the delays are noticeable.

I want to make the lines show exactly when a person starts speaking and they go away exactly when a person stops speaking. Can whisper do that?

Assume that I have an English movie that has French dialogue and I have a subtitle file for the French part. ChatGPT said that I can use whisper to generate a subtitle file for the movie and then the timing in that subtitle file will be used to fix the timing of my subtitle file and the command is:
python sync_subtitles.py my_movie.mp4 my_subtitles.srt

https://drive.google.com/file/d/1ShP5MmmOrr1CCuHPkPHhZgRKOVBzWyMt/view?usp=sharing is sync_subtitles.py that ChatGPT made.

After that it said this:
https://imgur.com/a/nCcZBm6

I said yes and it made for me a modified file which is modified_sync_subtitles.py and it is https://drive.google.com/file/d/1bvLnCeG9WUfXOydFCQWiUamj_-aS7sA_/view?usp=sharing. The modified script does this:
https://imgur.com/a/k0ql3OM

I want to ask is the coding in both scripts correct? Which script should I use?

[Advait251206]

About the model download failing

The error:

RuntimeError:
Model has been downloaded but the SHA256 checksum does not match.
Please retry loading the model.

usually means the model file is being downloaded incompletely or corrupted during download.

Since you mentioned:

18% -> fail
34% -> fail
55% -> fail

and you have an unstable internet connection, the most likely cause is an interrupted download leaving a partial .pt file behind.

Fix

Find Whisper's cache directory and delete the partially downloaded model.

Typically on Windows:

C:\Users\<YourUser>\.cache\whisper

Look for something like:

large-v3-turbo.pt

or a partially downloaded file and delete it.

You can also run:

import whisper
print(whisper.__file__)

to confirm where Whisper is installed.

Then try again.

Alternative: Download manually

If your connection keeps failing, you can manually download the model from the official Whisper model URL and place it in the Whisper cache directory.

The model URL can be found in Whisper's source code in:

whisper._MODELS

or in the Whisper repository.

This is often easier than repeatedly restarting a broken download.

---

Can Whisper make subtitles appear exactly when speech starts and ends?

Short answer

Partially, yes.

Whisper can generate:

• segment timestamps
• word timestamps

using:

whisper movie.mp4 --word_timestamps True

or:

model.transcribe(..., word_timestamps=True)

However, "exactly" is unrealistic.

Typical accuracy:

Segment timestamps:
±0.2–1.0 seconds

Word timestamps:
often ±50–300 ms

depending on:

• audio quality
• background noise
• music
• overlapping speakers

For subtitle synchronization, this is usually good enough.

---

Is Whisper the right tool for subtitle synchronization?

Yes.

A common workflow is:

Movie
↓
Whisper transcription
↓
Generate accurate timestamps
↓
Align existing subtitles
↓
Write corrected SRT

This is a standard approach used by many subtitle-sync tools.

---

About the scripts ChatGPT generated

Unfortunately I cannot verify whether:

sync_subtitles.py

or

modified_sync_subtitles.py

are correct because the code itself is not included in your post.

The links point to:

• Google Drive
• Imgur screenshots

and I cannot inspect those files unless the code is pasted directly.

---

My recommendation

Paste the actual contents of:

sync_subtitles.py

and

modified_sync_subtitles.py

(or upload them here).

Then I can:

• review the code
• check for bugs
• explain how it works
• compare both versions
• tell you which one is more reliable for subtitle synchronization

---

One more thing

If your goal is only subtitle synchronization, you may not need a custom script at all.

There are existing tools built specifically for this:

• :contentReference[oaicite:0]{index=0}
• :contentReference[oaicite:1]{index=1}
• :contentReference[oaicite:2]{index=2}

These tools are often faster and more robust than a custom Whisper-based script, especially when the subtitles already contain the correct text and only the timing is wrong.

For a detailed review, paste the Python code and I'll go through it line by line.