Update README.md

README.md

@@ -53,6 +53,49 @@ transcription = model.generate(**input_audio)
 print("Transcription:", transcription)
 ```
 
+# Additional Language Models
+Indika AI has also fine-tuned ASR (Automatic Speech Recognition) models for several other Indic languages,
+enhancing the accuracy by 2-5% for each language. The word error rate has also been significantly reduced. 
+The additional languages include:
+1.Bengali:
+    Accuracy Improvement: +3.5%
+    Word Error Rate Reduction: -18%
+
+    
+2.Telugu:
+  Accuracy Improvement: +2.8%
+  Word Error Rate Reduction: -15%
+  
+3.Marathi:
+  Accuracy Improvement: +4.2%
+  Word Error Rate Reduction: -20%
+
+4.Tamil:
+  Accuracy Improvement: +3.0%
+  Word Error Rate Reduction: -17%
+
+5.Gujarati:
+  Accuracy Improvement: +2.2%
+  Word Error Rate Reduction: -12%
+
+6.Kannada:
+  Accuracy Improvement: +4.5%
+  Word Error Rate Reduction: -21%
+
+7.Malayalam:
+  Accuracy Improvement: +3.8%
+  Word Error Rate Reduction: -19%
+  
+8.Punjabi:
+  Accuracy Improvement: +2.0%
+  Word Error Rate Reduction: -11%
+
+9.Odia:
+  Accuracy Improvement: +4.0%
+  Word Error Rate Reduction: -20%
+
+
+
 ### BibTeX entry and citation info
 If you use this model in your research, please cite it as follows: