docs: update readme

README.md

@@ -30,6 +30,16 @@ pipeline_tag: automatic-speech-recognition
 
 This repository contains a quantized version of the Indic Conformer model, a large-scale automatic speech recognition (ASR) model created for Indic languages by AI4Bharat. The original model can be found [here](https://huggingface.co/ai4bharat/indic-conformer-600m-multilingual)
 
+## Benchmarks
+
+These benchmarks were conducted on Google Colab free tier with Tesla T4 GPU for Hindi.
+You can use the notebooks in `scripts` directory to reproduce the results or compute for other languages. 
+
+| *Decoding Method* | FP 32 WER | int8 WER | FP32 CER | int8 CER |
+| ----------------- | --------- | -------- | -------- | -------- |
+| CTC               | 0.1645    | 0.2985   | 0.0661   | 0.1698   |
+| RNNT              | 0.1508    | 0.2939   | 0.0642   | 0.149    |
+
 ## Model Details
 
 - **Model Type**: Automatic Speech Recognition (ASR)
@@ -44,7 +54,7 @@ This model is intended for transcribing speech in Indic languages into text. It
 
 ## Usage
 
-[![Open in Kaggle](https://img.shields.io/badge/Open%20in-Kaggle-blue?logo=kaggle)](https://www.kaggle.com/code/haposeiz/using-indic-asr-quantized)
+Use the notebook: [![Open in Kaggle](https://img.shields.io/badge/Open%20in-Kaggle-blue?logo=kaggle)](https://www.kaggle.com/code/haposeiz/using-indic-asr-quantized)
 
 ### Installation
 
@@ -78,9 +88,7 @@ print(text)
 ## Model Files
 
 ### Config Sunfolder
-- `config.json`: Model configuration including architecture details, quantization settings, and RNN-T parameters
 - `vocab.json`: Subword vocabulary for supported languages
-- `preprocessor.json`: Preprocessor configuration for audio feature extraction
 - `language_masks.json`: Language-specific masks for handling multilingual inputs
 
 ### ONNX Subfolder
@@ -94,13 +102,13 @@ print(text)
 
 ## Training Data
 
-The model was quantized using a Calibration Dataset that can be found [here](https://www.kaggle.com/datasets/haposeiz/indicvoices-calibration-1408).
+Calibration Dataset:https://www.kaggle.com/datasets/haposeiz/indicvoices-calibration-1408
 
 The Calibration Dataset was curated from the [Indic Voices Dataset](https://huggingface.co/datasets/ai4bharat/IndicVoices).
 
 ## Additional Links
 
-- GitHub: https://github.com/atharva-again/indic-asr-onnx
+GitHub: https://github.com/atharva-again/indic-asr-onnx
 
 ## Contact
 

config/config.json

@@ -1,11 +0,0 @@
-{
-    "auto_map": {
-    "AutoConfig": "model_onnx.IndicASRConfig",
-    "AutoModel": "model_onnx.IndicASRModel"
-    },
-    "BLANK_ID": 256,
-    "RNNT_MAX_SYMBOLS": 10,
-    "PRED_RNN_LAYERS": 2,
-    "PRED_RNN_HIDDEN_DIM": 640,
-    "SOS": 256
-}