Update README.md

README.md

@@ -6,13 +6,13 @@ tags:
 - code-switching
 - ASR
 - multilingual
-license: "mit"
+license: mit
 datasets:
 - common_voice
 metrics:
 - wer
 - cer
-base_model: "facebook/wav2vec2-large-xls-r-300m"
+base_model: facebook/wav2vec2-large-xls-r-300m
 library_name: transformers
 model-index:
   - name: wav2vec2-large-xls-r-300m-hindi_marathi-code-switching-experiment
@@ -31,8 +31,9 @@ model-index:
             value: 0.2400
         source:
           name: Internal Evaluation
+          url: "https://huggingface.co/Hemantrao/wav2vec2-large-xls-r-300m-hindi_marathi-code-switching-experimentx1/"
 
-
+---
 # Enhanced Multilingual Code-Switched Speech Recognition for Low-Resource Languages Using Transformer-Based Models and Dynamic Switching Algorithms
 
 ## Model description
@@ -56,7 +57,6 @@ The model was fine-tuned using the following parameters:
 - Learning Rate: 3e-4
 - Mask Time Probability: 0.05
 
-For detailed training logs and experimental tracking, please refer to the [experiment tracking platform](link_to_experiment_tracking_platform).
 
 ## Training dataset
 The model was trained on the Common Voice dataset, which includes diverse speech samples in both Hindi and Marathi. The dataset was augmented with synthetically generated code-switched speech to improve the model's robustness in handling code-switching scenarios.
@@ -66,11 +66,3 @@ The model achieved the following performance metrics on the test set:
 - Word Error Rate (WER): 0.2800
 - Character Error Rate (CER): 0.2400
 
-## Ethical considerations and biases
-The model has potential biases due to the limited representation of accents, dialects, and socio-linguistic variations in the training data. Users should be cautious about deploying this model in critical applications without further evaluation and customization.
-
-## CO2 Emissions
-For information about the CO2 impact of training this model, please refer to our [guide on tracking and reporting CO2 emissions](link_to_CO2_impact_guide).
-
-## Paper
-If applicable, you can include a link to a paper describing this model. For instance, if your model is described in an arXiv paper, you can add the arXiv ID here: