Cant Transcribe Voice Samples #201

Closed
opened 2023-04-12 18:36:49 +00:00 by Nycz · 1 comment

image

First of all each and every one of my wav files (which work perfectly fine for normal voice cloning with the default model) fails transcribing (ive tried wav samples from different voice with different lengths using different settings all results in the same error).
Afterwards it justs tells me "Exception: Missing dataset: ./training/leon_re42023//whisper.json" which i presume is a symptom of the failed voice trainsribing.

Im running this on Windows11 with a rtx 3070 8GB

![image](/attachments/1f32da1b-2cba-4453-b1fe-e10e478abf47) First of all each and every one of my wav files (which work perfectly fine for normal voice cloning with the default model) fails transcribing (ive tried wav samples from different voice with different lengths using different settings all results in the same error). Afterwards it justs tells me "Exception: Missing dataset: ./training/leon_re42023//whisper.json" which i presume is a symptom of the failed voice trainsribing. Im running this on Windows11 with a rtx 3070 8GB
Author

Anyways i fixed this by reintalling ffmpeg and making sure it is in Path.

Anyways i fixed this by reintalling ffmpeg and making sure it is in Path.
Nycz closed this issue 2023-04-12 19:00:35 +00:00
Sign in to join this conversation.
No Milestone
No project
No Assignees
1 Participants
Notifications
Due Date
The due date is invalid or out of range. Please use the format 'yyyy-mm-dd'.

No due date set.

Dependencies

No dependencies set.

Reference: mrq/ai-voice-cloning#201
No description provided.