You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Hi!
I'm using the following command: insanely-fast-whisper --file-name intro.mp3 --language en
And I get an output.json which looks like this: { "speakers": [], "chunks": [{ "timestamp": [0.0, 4.7], "text": "bla bla bla" }, { "timestamp": [4.7, 7.7], "text": "bla bla bla" } ], "text": "bla bla bla bla bla bla" }
Is there any way to show the speaker_0, speaker_1 thing?
Thx!
The text was updated successfully, but these errors were encountered:
Hi! I'm using the following command: insanely-fast-whisper --file-name intro.mp3 --language en
And I get an output.json which looks like this: { "speakers": [], "chunks": [{ "timestamp": [0.0, 4.7], "text": "bla bla bla" }, { "timestamp": [4.7, 7.7], "text": "bla bla bla" } ], "text": "bla bla bla bla bla bla" }
Is there any way to show the speaker_0, speaker_1 thing? Thx!
You need to provide an Hugging Face authentication token for Pyannote.audio to diarise the audio clips. Pass it as arg to che command --hf-token
Hi!
I'm using the following command:
insanely-fast-whisper --file-name intro.mp3 --language en
And I get an output.json which looks like this:
{ "speakers": [], "chunks": [{ "timestamp": [0.0, 4.7], "text": "bla bla bla" }, { "timestamp": [4.7, 7.7], "text": "bla bla bla" } ], "text": "bla bla bla bla bla bla" }
Is there any way to show the speaker_0, speaker_1 thing?
Thx!
The text was updated successfully, but these errors were encountered: