This model is a fine-tuned version of openai/whisper-medium on the google/fleurs ps_af dataset. It achieves the following results on the evaluation set:
More information needed
More information needed
More information needed
The following hyperparameters were used during training:
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.0139 | 14.29 | 100 | 1.0302 | 50.1211 |
| 0.0011 | 28.57 | 200 | 1.2129 | 49.7806 |
| 0.0008 | 42.86 | 300 | 1.2581 | 50.3178 |
| 0.0007 | 57.14 | 400 | 1.2850 | 50.5524 |
| 0.0007 | 71.43 | 500 | 1.2950 | 50.6432 |
checkpoint-300/optimizer.pt 6.1 GBcheckpoint-400/optimizer.pt 6.1 GBcheckpoint-500/optimizer.pt 6.1 GBcheckpoint-100/optimizer.pt 6.1 GBcheckpoint-200/optimizer.pt 6.1 GBcheckpoint-100/pytorch_model.bin 3.1 GBcheckpoint-200/pytorch_model.bin 3.1 GBcheckpoint-300/pytorch_model.bin 3.1 GBcheckpoint-400/pytorch_model.bin 3.1 GBcheckpoint-500/pytorch_model.bin 3.1 GBpytorch_model.bin 3.1 GBcheckpoint-100/rng_state.pth 14.6 kBcheckpoint-200/rng_state.pth 14.6 kBcheckpoint-400/rng_state.pth 14.6 kBcheckpoint-500/rng_state.pth 14.6 kBcheckpoint-300/rng_state.pth 14.5 kBcheckpoint-100/training_args.bin 3.5 kBcheckpoint-200/training_args.bin 3.5 kBcheckpoint-300/training_args.bin 3.5 kBcheckpoint-400/training_args.bin 3.5 kBcheckpoint-500/training_args.bin 3.5 kBtraining_args.bin 3.5 kBcheckpoint-100/scheduler.pt 0.6 kBcheckpoint-200/scheduler.pt 0.6 kBcheckpoint-300/scheduler.pt 0.6 kBcheckpoint-400/scheduler.pt 0.6 kBcheckpoint-500/scheduler.pt 0.6 kBcheckpoint-100/scaler.pt 0.6 kBcheckpoint-200/scaler.pt 0.6 kBcheckpoint-300/scaler.pt 0.6 kBcheckpoint-400/scaler.pt 0.6 kBcheckpoint-500/scaler.pt 0.6 kB