final

README.md

@@ -1,24 +1,25 @@
 ---
 language:
-- en
+  - en
 license: apache-2.0
 base_model: openai/whisper-tiny
 tags:
-- generated_from_trainer
+  - generated_from_trainer
 metrics:
-- wer
+  - wer
 model-index:
-- name: Deepakr07
-  results: []
+  - name: Deepakr07
+    results: []
 ---
 
 <!-- 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. -->
 
-# whispertiny-shreyas
+# Deepakr07-whisper_finetune
 
 This model is a fine-tuned version of [Whisper Tiny](https://huggingface.co/openai/whisper-tiny) on the [AI4Bharat-svarah](https://github.com/AI4Bharat/Svarah) dataset.
 It achieves the following results on the evaluation set:
+
 - Loss: 0.5414
 - Wer: 22.8322
 
@@ -30,14 +31,14 @@ The models were trained on either English-only data or multilingual data. The En
 
 Whisper checkpoints come in five configurations of varying model sizes. The smallest four are trained on either English-only or multilingual data. The largest checkpoints are multilingual only. All ten of the pre-trained checkpoints are available on the Hugging Face Hub. The checkpoints are summarised in the following table with links to the models on the Hub:
 
-
 ## Training procedure
 
-Refer to [Sanchit's blog](https://huggingface.co/blog/fine-tune-whisper) and make changes according to the dependencies' version you have. 
+Refer to [Sanchit's blog](https://huggingface.co/blog/fine-tune-whisper) and make changes according to the dependencies' version you have.
 
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
+
 - learning_rate: 1e-05
 - train_batch_size: 8
 - eval_batch_size: 8
@@ -52,11 +53,10 @@ The following hyperparameters were used during training:
 
 ### Training results
 
-| Training Loss | Epoch  | Step | Validation Loss | Wer     |
-|:-------------:|:------:|:----:|:---------------:|:-------:|
-| 0.2412        | 2.6702 | 1000 | 0.5319          | 22.8914 |
-| 0.1071        | 5.3405 | 2000 | 0.5414          | 22.8322 |
-
+| Training Loss | Epoch  | Step | Validation Loss |   Wer   |
+| :-----------: | :----: | :--: | :-------------: | :-----: |
+|    0.2412     | 2.6702 | 1000 |     0.5319      | 22.8914 |
+|    0.1071     | 5.3405 | 2000 |     0.5414      | 22.8322 |
 
 ### Framework versions