Update README.md

README.md

@@ -13,7 +13,7 @@ pipeline_tag: automatic-speech-recognition
 
 
 A 17.31M parameter multilingual linear projector trained for automatic speech recognition (ASR) using the SLAM-ASR speechLLM framework. 
-Within this framework, only the linear projector was trained alongisde a frozen speech encoder ([Whisper-large-v3-turbo](https://huggingface.co/openai/whisper-large-v3-turbo))
+Within this framework, only the linear projector was trained alongside a frozen speech encoder ([Whisper-large-v3-turbo](https://huggingface.co/openai/whisper-large-v3-turbo))
 and frozen LLM ([EuroLLM-1.7B](https://huggingface.co/utter-project/EuroLLM-1.7B)). 
 
 - **Developed by:** SpeechTek Unit at Fondazione Bruno Kessler
@@ -28,7 +28,7 @@ This model is trained for Automatic Speech Recognition (ASR).
 
 ## How to Get Started with the Model
 
-This linear projector can be used using the shell scripts provided in the [SLAM-ASR](https://github.com/X-LANCE/SLAM-LLM/tree/main/examples/asr_librispeech) codebase. Kindly refer to the instructions there with regards to data preparation and decoding.
+This linear projector can be used using the shell scripts provided in the [SLAM-ASR](https://github.com/X-LANCE/SLAM-LLM/tree/main/examples/asr_librispeech) codebase. Kindly refer to the instructions there for further details.
 
 Whisper-large-v3-turbo and EuroLLM 1.7B must be downloaded before using this linear projector.
 
@@ -41,11 +41,12 @@ Specifically, the training set consisted of 92.5 hours of Common Voice data + 7.
 
 ### Training Procedure
 
-The linear projector was trained using the code-based provided by the official [SLAM-ASR Github repository](https://github.com/X-LANCE/SLAM-LLM/tree/main/examples/asr_librispeech) with `torchrun`.
-Only the linear projector was trained. The whisper-large-v3-turbo speech encoder (Whisper-large-v3-turbo](https://huggingface.co/openai/whisper-large-v3-turbo))
+* The linear projector was trained using the code-based provided by the official [SLAM-ASR Github repository](https://github.com/X-LANCE/SLAM-LLM/tree/main/examples/asr_librispeech) with `torchrun`.
+* Only the linear projector was trained.
+* The whisper-large-v3-turbo speech encoder (Whisper-large-v3-turbo](https://huggingface.co/openai/whisper-large-v3-turbo))
 and LLM ([EuroLLM-1.7B](https://huggingface.co/utter-project/EuroLLM-1.7B)) were kept frozen.
-
-Training was conducted with one NVIDIA Ada Lovelace L40S GPU.
+* No prompt was used during training and inference 
+* Training was conducted with one NVIDIA Ada Lovelace L40S GPU.
 
 
 #### Training Hyperparameters
@@ -79,6 +80,9 @@ Training was conducted with one NVIDIA Ada Lovelace L40S GPU.
 
 ## Evaluation
 
+The model was evaluated using the Word Error Rate (WER) metric from the `evaluate` library. 
+Prior to computing the WER, preprocessing of ground-truth and predicted transcripts was carried out using the `Whisper EnglishTextNormalizer` for English and `BasicTextNormalizer` for all other languages. 
+
 ### Results
 
 [More Information Needed]