Update README.md

README.md

@@ -3,11 +3,18 @@ library_name: transformers
 license: apache-2.0
 base_model: openai/whisper-large-v3
 tags:
-- generated_from_trainer
+- automatic-speech-recognition
+- whisper
+- urdu
+- mozilla-foundation/common_voice_17_0
+- hf-asr-leaderboard
 datasets:
-- common_voice_17_0
+- mozilla-foundation/common_voice_17_0
 metrics:
 - wer
+- cer
+- bleu
+- chrf
 model-index:
 - name: whisper-large-v3-urdu
   results:
@@ -15,21 +22,33 @@ model-index:
       type: automatic-speech-recognition
       name: Automatic Speech Recognition
     dataset:
-      name: common_voice_17_0
-      type: common_voice_17_0
+      name: Common Voice 17.0 (Urdu)
+      type: mozilla-foundation/common_voice_17_0
       config: ur
-      split: test[:600]
+      split: test
       args: ur
     metrics:
     - type: wer
-      value: 21.47124719940254
-      name: Wer
+      value: 26.234
+      name: WER
+    - type: cer
+      value: 8.795
+      name: CER
+    - type: bleu
+      value: 58.032
+      name: BLEU
+    - type: chrf
+      value: 81.636
+      name: ChrF
+language:
+- ur
+pipeline_tag: automatic-speech-recognition
 ---
 
 <!-- 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-large-v3-urdu
+# Whisper large V3 Urdu ASR Model 🥇
 
 This model is a fine-tuned version of [openai/whisper-large-v3](https://huggingface.co/openai/whisper-large-v3) on the common_voice_17_0 dataset.
 It achieves the following results on the evaluation set:
@@ -37,19 +56,28 @@ It achieves the following results on the evaluation set:
 - Wer: 21.4712
 - Cer: 7.1975
 
-## Model description
 
-More information needed
+## Quick Usage
 
-## Intended uses & limitations
+```python
+from transformers import pipeline
 
-More information needed
+transcriber = pipeline(
+  "automatic-speech-recognition", 
+  model="kingabzpro/whisper-large-v3-turbo-urdu"
+)
 
-## Training and evaluation data
+transcriber.model.generation_config.forced_decoder_ids = None
+transcriber.model.generation_config.language = "ur"
 
-More information needed
+transcription = transcriber("audio2.mp3")
+print(transcription)
+```
+
+```sh
+{'text': 'دیکھیے پانی کب تک بہتا اور مچھلی کب تک تیرتی ہے'}
+```
 
-## Training procedure
 
 ### Training hyperparameters
 
@@ -82,3 +110,19 @@ The following hyperparameters were used during training:
 - Pytorch 2.7.1+cu126
 - Datasets 3.4.1
 - Tokenizers 0.21.2
+
+---
+
+## Evaluation
+
+Urdu ASR Evaluation on Common Voice 17.0 (Test Split). 
+
+| Metric | Value    | Description                        |
+|--------|----------|------------------------------------|
+| **WER**   | 26.234%  | Word Error Rate (lower is better) |
+| **CER**   | 8.795%   | Character Error Rate              |
+| **BLEU**  | 58.032%  | BLEU Score (higher is better)     |
+| **ChrF**  | 81.636   | Character n-gram F-score          |
+
+>👉 Review the testing script: [Testing Whisper Large V3 Urdu](https://www.kaggle.com/code/kingabzpro/testing-urdu-asr-using-unsloth)
+