End of training

README.md

@@ -3,26 +3,11 @@ license: mit
 base_model: Harveenchadha/vakyansh-wav2vec2-hindi-him-4200
 tags:
 - generated_from_trainer
-datasets:
-- fleurs
 metrics:
 - wer
 model-index:
 - name: hindi_wav2vec2_optimized
-  results:
-  - task:
-      name: Automatic Speech Recognition
-      type: automatic-speech-recognition
-    dataset:
-      name: fleurs
-      type: fleurs
-      config: hi_in
-      split: test
-      args: hi_in
-    metrics:
-    - name: Wer
-      type: wer
-      value: 0.4386410231377526
+  results: []
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -30,10 +15,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # hindi_wav2vec2_optimized
 
-This model is a fine-tuned version of [Harveenchadha/vakyansh-wav2vec2-hindi-him-4200](https://huggingface.co/Harveenchadha/vakyansh-wav2vec2-hindi-him-4200) on the fleurs dataset.
+This model is a fine-tuned version of [Harveenchadha/vakyansh-wav2vec2-hindi-him-4200](https://huggingface.co/Harveenchadha/vakyansh-wav2vec2-hindi-him-4200) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 2.2950
-- Wer: 0.4386
+- Loss: 4.5032
+- Wer: 1.0
 
 ## Model description
 
@@ -65,18 +50,18 @@ The following hyperparameters were used during training:
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss | Wer    |
-|:-------------:|:-----:|:----:|:---------------:|:------:|
-| 3.8474        | 10.0  | 25   | 2.0026          | 0.5689 |
-| 0.5389        | 20.0  | 50   | 2.0278          | 0.4474 |
-| 0.4199        | 30.0  | 75   | 2.1555          | 0.4512 |
-| 0.1534        | 40.0  | 100  | 2.2412          | 0.4766 |
-| 0.096         | 50.0  | 125  | 2.2013          | 0.4593 |
-| 0.0574        | 60.0  | 150  | 2.1777          | 0.4657 |
-| 0.0361        | 70.0  | 175  | 2.4166          | 0.4391 |
-| 0.0278        | 80.0  | 200  | 2.2826          | 0.4571 |
-| 0.025         | 90.0  | 225  | 2.3623          | 0.4433 |
-| 0.0157        | 100.0 | 250  | 2.2950          | 0.4386 |
+| Training Loss | Epoch | Step | Validation Loss | Wer |
+|:-------------:|:-----:|:----:|:---------------:|:---:|
+| 4.9191        | 10.0  | 25   | 4.5585          | 1.0 |
+| 4.5288        | 20.0  | 50   | 4.5183          | 1.0 |
+| 4.5144        | 30.0  | 75   | 4.5047          | 1.0 |
+| 4.5182        | 40.0  | 100  | 4.5080          | 1.0 |
+| 4.5124        | 50.0  | 125  | 4.5108          | 1.0 |
+| 4.5113        | 60.0  | 150  | 4.5041          | 1.0 |
+| 4.5126        | 70.0  | 175  | 4.5036          | 1.0 |
+| 4.5093        | 80.0  | 200  | 4.5035          | 1.0 |
+| 4.5098        | 90.0  | 225  | 4.5047          | 1.0 |
+| 4.5089        | 100.0 | 250  | 4.5032          | 1.0 |
 
 
 ### Framework versions

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5b85d79b565865f84847a029c384e341bf7c82000b62dbf4358252eb8c39f0db
+oid sha256:1fed34610075020d594bafc63329c74c1cb1b314b690520b4ee0cf7e5772cfb4
 size 377766433