This model is a fine-tuned version of Qwen/Qwen3-ASR-0.6B-hf on an unknown 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 |
|---|---|---|---|
| 1.5273 | 0.2746 | 500 | 1.4938 |
| 1.1306 | 0.5491 | 1000 | 1.1212 |
| 0.9481 | 0.8237 | 1500 | 0.9669 |
| 0.8965 | 1.0983 | 2000 | 0.8827 |
| 0.8434 | 1.3729 | 2500 | 0.8288 |
| 0.7885 | 1.6474 | 3000 | 0.7924 |
| 0.7970 | 1.9220 | 3500 | 0.7620 |
| 0.7295 | 2.1966 | 4000 | 0.7407 |
| 0.6923 | 2.4712 | 4500 | 0.7276 |
| 0.6773 | 2.7457 | 5000 | 0.7188 |
| 0.6960 | 3.0 | 5463 | 0.7159 |
checkpoint-5463/optimizer.pt 94 MBlast-checkpoint/optimizer.pt 94 MBadapter_model.safetensors 47 MBcheckpoint-5463/adapter_model.safetensors 47 MBlast-checkpoint/adapter_model.safetensors 47 MBcheckpoint-5463/rng_state_0.pth 14.9 kBcheckpoint-5463/rng_state_1.pth 14.9 kBlast-checkpoint/rng_state_0.pth 14.9 kBlast-checkpoint/rng_state_1.pth 14.9 kBcheckpoint-5463/training_args.bin 5.3 kBlast-checkpoint/training_args.bin 5.3 kBtraining_args.bin 5.3 kBcheckpoint-5463/scheduler.pt 1.5 kBlast-checkpoint/scheduler.pt 1.5 kBcheckpoint-5463/scaler.pt 1.4 kBlast-checkpoint/scaler.pt 1.4 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 taqbaylit/qwen3-asr-0.6b-kabyle ./model-folderQwen/Qwen3-ASR-0.6B-hf