faster-whisper-small-nya-tknSW

README.md

@@ -4,6 +4,8 @@ license: apache-2.0
 base_model: openai/whisper-small
 tags:
 - generated_from_trainer
+metrics:
+- wer
 model-index:
 - name: output
   results: []
@@ -16,14 +18,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- eval_loss: 0.5583
-- eval_wer: 0.3817
-- eval_cer: 0.1696
-- eval_runtime: 258.7829
-- eval_samples_per_second: 2.404
-- eval_steps_per_second: 0.301
-- epoch: 8.6621
-- step: 2200
+- Loss: 0.5610
+- Wer: 0.4369
+- Cer: 0.2391
 
 ## Model description
 
@@ -54,6 +51,23 @@ The following hyperparameters were used during training:
 - training_steps: 10000
 - mixed_precision_training: Native AMP
 
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss | Wer    | Cer    |
+|:-------------:|:------:|:----:|:---------------:|:------:|:------:|
+| 0.9794        | 0.7882 | 200  | 1.4261          | 0.7751 | 0.2368 |
+| 0.4482        | 1.5754 | 400  | 0.9341          | 0.5545 | 0.1791 |
+| 0.2978        | 2.3626 | 600  | 0.7387          | 0.4951 | 0.1833 |
+| 0.2087        | 3.1498 | 800  | 0.6379          | 0.6575 | 0.3344 |
+| 0.1782        | 3.9379 | 1000 | 0.5686          | 0.3875 | 0.1540 |
+| 0.1275        | 4.7251 | 1200 | 0.5456          | 0.3472 | 0.1295 |
+| 0.0894        | 5.5123 | 1400 | 0.5294          | 0.4248 | 0.2279 |
+| 0.05          | 6.2995 | 1600 | 0.5384          | 0.3768 | 0.1744 |
+| 0.0471        | 7.0867 | 1800 | 0.5511          | 0.5286 | 0.3003 |
+| 0.0297        | 7.8749 | 2000 | 0.5557          | 0.3863 | 0.1668 |
+| 0.0167        | 8.6621 | 2200 | 0.5610          | 0.4369 | 0.2391 |
+
+
 ### Framework versions
 
 - Transformers 4.57.1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5cfbfffc70d72c26881529282becd5ed28239d79c1030c2e604ad528e6b39829
+oid sha256:0250c7439015f6f7fdf7046ed3085c52239de560e4628f34661618d07370bbdf
 size 966995080

runs/Oct25_10-25-27_e51d2280198c/events.out.tfevents.1761387932.e51d2280198c.1869.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:93a41e6c0e6f744bdd26a5087bff99f55a18f61baa131db23ec0e1db411ad97e
+size 20404

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:48ad6fbcdc07081456b07bf1623eb091788258f477313dce9ab172ef6f2090c6
+oid sha256:55350a2ab7e440e3e8a3bfda778c9ef42b5a0fcf176554ec69d124954ab98900
 size 5969