End of training

README.md

@@ -2,19 +2,19 @@
 language:
 - hi
 license: apache-2.0
+base_model: openai/whisper-small
 tags:
 - generated_from_trainer
-base_model: openai/whisper-small
 datasets:
 - mozilla-foundation/common_voice_11_0
 metrics:
 - wer
 model-index:
-- name: Whisper Model Hindi(small) - Tashu Gurnani
+- name: Whisper small hindi2 - Tashu Gurnani
   results:
   - task:
-      type: automatic-speech-recognition
       name: Automatic Speech Recognition
+      type: automatic-speech-recognition
     dataset:
       name: Common Voice 11.0
       type: mozilla-foundation/common_voice_11_0
@@ -22,20 +22,20 @@ model-index:
       split: None
       args: 'config: hi, split: test'
     metrics:
-    - type: wer
-      value: 34.466265978159655
-      name: Wer
+    - name: Wer
+      type: wer
+      value: 33.010242952679256
 ---
 
 <!-- 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 Model Hindi(small) - Tashu Gurnani
+# Whisper small hindi2 - Tashu Gurnani
 
 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: 0.2860
-- Wer: 34.4663
+- Loss: 0.3303
+- Wer: 33.0102
 
 ## Model description
 
@@ -61,19 +61,20 @@ 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: 1000
+- training_steps: 2000
 - mixed_precision_training: Native AMP
 
 ### Training results
 
-| Training Loss | Epoch  | Step | Validation Loss | Wer     |
-|:-------------:|:------:|:----:|:---------------:|:-------:|
-| 0.0819        | 2.4450 | 1000 | 0.2860          | 34.4663 |
+| Training Loss | Epoch | Step | Validation Loss | Wer     |
+|:-------------:|:-----:|:----:|:---------------:|:-------:|
+| 0.0884        | 2.44  | 1000 | 0.2946          | 34.7668 |
+| 0.0173        | 4.89  | 2000 | 0.3303          | 33.0102 |
 
 
 ### Framework versions
 
-- Transformers 4.41.0
-- Pytorch 2.3.0+cu121
-- Datasets 2.19.1
-- Tokenizers 0.19.1
+- Transformers 4.39.3
+- Pytorch 2.1.2
+- Datasets 2.18.0
+- Tokenizers 0.15.2

generation_config.json

@@ -252,5 +252,5 @@
     "transcribe": 50359,
     "translate": 50358
   },
-  "transformers_version": "4.41.0"
+  "transformers_version": "4.39.3"
 }