End of training

README.md

@@ -10,7 +10,7 @@ datasets:
 metrics:
 - wer
 model-index:
-- name: Whisper_Small_Hi-DevHarsh
+- name: Hindi Whisper Model
   results:
   - task:
       name: Automatic Speech Recognition
@@ -19,23 +19,23 @@ model-index:
       name: Common Voice 11.0
       type: mozilla-foundation/common_voice_11_0
       config: hi
-      split: None
+      split: test
       args: 'config: hi, split: test'
     metrics:
     - name: Wer
       type: wer
-      value: 33.12875645475324
+      value: 34.38584610175231
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 should probably proofread and complete it, then remove this comment. -->
 
-# Whisper_Small_Hi-DevHarsh
+# Hindi Whisper Model
 
 This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the Common Voice 11.0 dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.3303
-- Wer: 33.1288
+- Loss: 0.2859
+- Wer: 34.3858
 
 ## Model description
 
@@ -61,20 +61,19 @@ 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
-- training_steps: 2000
+- training_steps: 1000
 - mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch  | Step | Validation Loss | Wer     |
 |:-------------:|:------:|:----:|:---------------:|:-------:|
-| 0.0884        | 2.4450 | 1000 | 0.2942          | 34.8345 |
-| 0.0175        | 4.8900 | 2000 | 0.3303          | 33.1288 |
+| 0.0818        | 2.4450 | 1000 | 0.2859          | 34.3858 |
 
 
 ### Framework versions
 
 - Transformers 4.41.2
-- Pytorch 2.3.0+cu121
+- Pytorch 2.1.2
 - Datasets 2.20.0
 - Tokenizers 0.19.1