whisper-at

whisper-at copied to clipboard

Using custom trained whisper-at model

1

Hi Yuan, I custom trained my own model using your training recipe. I followed instructions and successfully ran run_as_full_train.sh with my custom dataset. However, I'm having trouble importing the model...

himacks

ResolutionImpossible error

9

Hi, When I use: pip install whisper-at I get: Defaulting to user installation because normal site-packages is not writeable Collecting whisper-at Downloading whisper_at-0.5-py3-none-any.whl.metadata (20 kB) INFO: pip is looking at...

orionflame

Possible use faster-whisper (https://github.com/guillaumekln/faster-whisper) backend?

5

tensorboy

Hi, I have a lot of narration done by myself for a tutorial that I made so I am trying to clean up the audio files to remove anything non...

orionflame

Thanks for the great code! Can you explain if and how it's possible to train a whisper-at model based on a fine-tuned whisper model? Maybe a more general question, if...

Ar770

Is transcription with JAX-able models and subsequent labeling with whisper-at possible? Or does the transcription result need to be from whisper-at? Im wondering because of how fast whisper-jax is, I...

WhyAreYouJay

I believe[ this commit in whisper](https://github.com/openai/whisper/commit/8bc8860694949db53c42ba47ddc23786c2e02a8b) addresses the issue of installing whisper-at described in #2 I simply tried to copy over all the changes in the whisper update. With this...

shawnCaza

Support for whisper-large-v3

1

Hello, First of all, nice work! Is it possible to release a checkpoint trained with whisper-large-v3? The reason I'm interested in this is that large-v3 is trained on a new...

spaghettiSystems

Number of Classes is 3 Now load features from /data/sls/scratch/yuangong/whisper-a/feat_as_full/whisper_tiny Dataset has 31 samples Using Label Smoothing: 0.0 Using Following Mask: 0 Freq, 0 Time Using Mix-up with Rate 0.000000...

herbiel

how to inference with batch?

1

Hello, thank you for sharing really nice code. However, I cannot find batch-wise inference codes for transcribing . (I referred quick start example code in ReadMe) Is there any batch-wise...

dinoSpeech