Spaces:
Runtime error
Runtime error
Update README
Browse files
README.md
CHANGED
|
@@ -54,11 +54,15 @@ When more than one file is processed, the UI will also generate a "All_Output" z
|
|
| 54 |
|
| 55 |
## Diarization
|
| 56 |
|
| 57 |
-
To detect different speakers in the audio, you can use the [whisper-diarization](https://gitlab.com/aadnk/whisper-diarization) application.
|
| 58 |
|
| 59 |
Download the JSON file after running Whisper on an audio file, and then run app.py in the
|
| 60 |
whisper-diarization repository with the audio file and the JSON file as arguments.
|
| 61 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 62 |
## Whisper Implementation
|
| 63 |
|
| 64 |
You can choose between using `whisper` or `faster-whisper`. [Faster Whisper](https://github.com/guillaumekln/faster-whisper) as a drop-in replacement for the
|
|
|
|
| 54 |
|
| 55 |
## Diarization
|
| 56 |
|
| 57 |
+
To detect different speakers in the audio, you can use the [whisper-diarization](https://gitlab.com/aadnk/whisper-diarization) application, or check "Diarization" in the options.
|
| 58 |
|
| 59 |
Download the JSON file after running Whisper on an audio file, and then run app.py in the
|
| 60 |
whisper-diarization repository with the audio file and the JSON file as arguments.
|
| 61 |
|
| 62 |
+
## Translation
|
| 63 |
+
|
| 64 |
+
To translate the transcript to English, set the task to "Translate". You can also use ChatGPT for this task via my [translate-gpt](https://gitlab.com/aadnk/translate-gpt) CLI application.
|
| 65 |
+
|
| 66 |
## Whisper Implementation
|
| 67 |
|
| 68 |
You can choose between using `whisper` or `faster-whisper`. [Faster Whisper](https://github.com/guillaumekln/faster-whisper) as a drop-in replacement for the
|