This model is a fine-tuned version of openai/whisper-medium on the mozilla-foundation/common_voice_11_0 ur 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 |
|---|---|---|---|---|
| 0.3908 | 0.48 | 100 | 0.5148 | 30.7061 |
| 0.3519 | 0.97 | 200 | 0.4685 | 26.9801 |
| 0.2426 | 1.45 | 300 | 0.4636 | 28.5023 |
@article{hanif2023whisper,
title={Whisper Medium Urdu Model},
author={Hanif, Rahman},
howpublished={\url{https://huggingface.co/ihanif/whisper-medium-urdu}},
year={2023}
}
checkpoint-300/optimizer.pt 6.1 GBcheckpoint-200/optimizer.pt 6.1 GBcheckpoint-200/pytorch_model.bin 3.1 GBcheckpoint-300/pytorch_model.bin 3.1 GBpytorch_model.bin 3.1 GBmodel.safetensors 3.1 GBcheckpoint-200/rng_state.pth 14.6 kBcheckpoint-300/rng_state.pth 14.6 kBcheckpoint-200/training_args.bin 3.6 kBcheckpoint-300/training_args.bin 3.6 kBtraining_args.bin 3.6 kBcheckpoint-200/scheduler.pt 0.6 kBcheckpoint-300/scheduler.pt 0.6 kBcheckpoint-200/scaler.pt 0.6 kBcheckpoint-300/scaler.pt 0.6 kBHave the files? Submit a torrent.
Submit a torrentHave the complete files and permission to share them? Replace the example folder path. The script checks the files, makes a torrent and submits its magnet and checksums. Keep your torrent client seeding. Get your community key from your settings, and read the script before running it.
curl -fsSL https://pirateface.co/package.sh | bash -s -- --repo ihanif/whisper-medium-urdu ./model-folder