Views
No views yet
Flutra/whisper-large-v3-turbo-sq-v2, optimized for use with Faster Whisper and WhisperX.openai/whisper-large-v3-turbosq)| Argument | Value |
|---|---|
per_device_train_batch_size | 8 |
gradient_accumulation_steps | 1 |
num_train_epochs | 3 |
learning_rate | 1e-5 |
fp16 | True |