End of training

README.md

@@ -7,9 +7,22 @@ tags:
 - generated_from_trainer
 datasets:
 - velocity-whisper
+metrics:
+- wer
 model-index:
 - name: whisper-small-finetuned-hinglish
-  results: []
+  results:
+  - task:
+      name: Automatic Speech Recognition
+      type: automatic-speech-recognition
+    dataset:
+      name: exclamation
+      type: velocity-whisper
+      args: 'config: hi, split: test'
+    metrics:
+    - name: Wer
+      type: wer
+      value: 17.393238434163703
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -18,6 +31,9 @@ should probably proofread and complete it, then remove this comment. -->
 # whisper-small-finetuned-hinglish
 
 This model is a fine-tuned version of [openai/whisper-medium](https://huggingface.co/openai/whisper-medium) on the exclamation dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.2420
+- Wer: 17.3932
 
 ## Model description
 
@@ -43,11 +59,21 @@ The following hyperparameters were used during training:
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_steps: 500
-- num_epochs: 2
+- num_epochs: 30
 - mixed_precision_training: Native AMP
 
 ### Training results
 
+| Training Loss | Epoch   | Step | Validation Loss | Wer     |
+|:-------------:|:-------:|:----:|:---------------:|:-------:|
+| 0.0344        | 3.6765  | 1000 | 0.1656          | 18.9057 |
+| 0.0077        | 7.3529  | 2000 | 0.2077          | 19.5878 |
+| 0.0043        | 11.0294 | 3000 | 0.2179          | 17.6453 |
+| 0.0014        | 14.7059 | 4000 | 0.2176          | 16.8594 |
+| 0.0007        | 18.3824 | 5000 | 0.2293          | 16.6518 |
+| 0.0           | 22.0588 | 6000 | 0.2318          | 16.0587 |
+| 0.0           | 25.7353 | 7000 | 0.2384          | 17.4822 |
+| 0.0           | 29.4118 | 8000 | 0.2420          | 17.3932 |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:afe89bd2f457c8357c955402b07e4a3970b28381e16acecf23960cf8068b8479
+oid sha256:bc51cff5efe3ea81afdd5e4fd44b6a3742bdcdef0171a6f635929a343292263a
 size 3055544304

runs/Jun02_08-47-29_cba442867bcc/events.out.tfevents.1717318051.cba442867bcc.891.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ac1ee1a4fad2b4fa5b774bb36f7090f7790daa0fa7d7c38974eec84c09c0609d
-size 76667
+oid sha256:84b28d2d6756b23086eab6abc8395383a44d8d3d8b6c526a50c61b4efe68fb8f
+size 78287