Spaces:
Running
Running
abdullah-alnahas
commited on
Commit
·
ed4e2cc
1
Parent(s):
e9f148d
docs(README.md): update readme
Browse files- README.md +8 -4
- screenshot.png +0 -0
README.md
CHANGED
@@ -1,13 +1,15 @@
|
|
1 |
# YouTube Video Transcriber
|
2 |
|
3 |
-
A Streamlit app that transcribes YouTube videos using Whisper.
|
4 |
|
5 |
## How it works
|
6 |
|
7 |
-
- Downloads audio from YouTube videos
|
8 |
- Splits audio into speech segments using Silero VAD.
|
9 |
- Transcribes segments in batches using OpenAI's Whisper model.
|
|
|
10 |
- Displays transcribed text with timestamps.
|
|
|
11 |
|
12 |
## Requirements
|
13 |
|
@@ -17,8 +19,10 @@ Listed in `requirements.txt`
|
|
17 |
|
18 |
1. Install dependencies: `pip install -r requirements.txt`
|
19 |
2. Run the app: `streamlit run app.py`
|
20 |
-
3. Enter a YouTube video URL
|
21 |
-
4.
|
|
|
|
|
22 |
|
23 |
## Screenshot
|
24 |
|
|
|
1 |
# YouTube Video Transcriber
|
2 |
|
3 |
+
A Streamlit app that transcribes YouTube videos using Whisper, with optional formatting using a large language model, audio download, and video download.
|
4 |
|
5 |
## How it works
|
6 |
|
7 |
+
- Downloads audio from YouTube videos using `yt-dlp`.
|
8 |
- Splits audio into speech segments using Silero VAD.
|
9 |
- Transcribes segments in batches using OpenAI's Whisper model.
|
10 |
+
- Formats the transcription using a large language model (if selected).
|
11 |
- Displays transcribed text with timestamps.
|
12 |
+
- Provides options to download the raw transcription, formatted transcription, audio, or video.
|
13 |
|
14 |
## Requirements
|
15 |
|
|
|
19 |
|
20 |
1. Install dependencies: `pip install -r requirements.txt`
|
21 |
2. Run the app: `streamlit run app.py`
|
22 |
+
3. Enter a YouTube video URL.
|
23 |
+
4. Choose options: Transcribe, Download Audio, Download Video, Format Text.
|
24 |
+
5. Select a language or use auto-detect (under "Advanced Settings").
|
25 |
+
6. Click "Process".
|
26 |
|
27 |
## Screenshot
|
28 |
|
screenshot.png
CHANGED