Update README.md

README.md

@@ -1,6 +1,6 @@
 ---
 language:
-- hi
+- ar
 thumbnail: null
 pipeline_tag: automatic-speech-recognition
 tags:
@@ -16,31 +16,31 @@ metrics:
 - wer
 - cer
 model-index:
-- name: asr-whisper-large-v2-commonvoice-ar
+- name: asr-whisper-medium-commonvoice-ar
   results:
   - task:
       name: Automatic Speech Recognition
       type: automatic-speech-recognition
     dataset:
-      name: CommonVoice 10.0 (Hindi)
-      type: mozilla-foundation/common_voice_10_0
-      config: hi
+      name: CommonVoice 10.0 (Arabic)
+      type: mozilla-foundation/common_voice_14_0
+      config: ar
       split: test
       args:
-        language: hi
+        language: ar
     metrics:
     - name: Test WER
       type: wer
-      value: '15.27'
+      value: '14.82'
 ---
 
-<iframe src="https://ghbtns.com/github-btn.html?user=speechbrain&repo=speechbrain&type=star&count=true&size=large&v=2" frameborder="0" scrolling="0" width="170" height="30" title="GitHub"></iframe>
+<iframe src="https://ghbtns.com/github-btn.html?user=speechbrain&repo=speechbrain&type=star&count=true&size=medium" frameborder="0" scrolling="0" width="170" height="30" title="GitHub"></iframe>
 <br/><br/>
 
-# whisper large-v2 fine-tuned on CommonVoice Hindi
+# whisper medium fine-tuned on CommonVoice-14.0 Arabic
 
 This repository provides all the necessary tools to perform automatic speech
-recognition from an end-to-end whisper model fine-tuned on CommonVoice (Hindi Language) within
+recognition from an end-to-end whisper model fine-tuned on CommonVoice (Arabic Language) within
 SpeechBrain. For a better experience, we encourage you to learn more about
 [SpeechBrain](https://speechbrain.github.io).
 
@@ -48,14 +48,14 @@ The performance of the model is the following:
 
 | Release | Test CER | Test WER | GPUs |
 |:-------------:|:--------------:|:--------------:| :--------:|
-| 01-02-23 | 7.00 |  15.27 | 1xV100 16GB |
+| 1-08-23 | 4.95 |  14.82 | 1xV100 32GB |
 
 ## Pipeline description
 
 This ASR system is composed of whisper encoder-decoder blocks:
-- The pretrained whisper-large-v2 encoder is frozen.
+- The pretrained whisper-medium encoder is frozen.
 - The pretrained Whisper tokenizer is used.
-- A pretrained Whisper-large-v2 decoder ([openai/whisper-large-v2](https://huggingface.co/openai/whisper-large-v2)) is finetuned on CommonVoice hi.
+- A pretrained Whisper-medium decoder ([openai/whisper-medium](https://huggingface.co/openai/whisper-medium)) is finetuned on CommonVoice ar.
 The obtained final acoustic representation is given to the greedy decoder. 
 
 The system is trained with recordings sampled at 16kHz (single channel).
@@ -66,20 +66,20 @@ The code will automatically normalize your audio (i.e., resampling + mono channe
 First of all, please install tranformers and SpeechBrain with the following command:
 
 ```
-pip install speechbrain transformers==4.28.0
+pip install speechbrain transformers
 ```
 
 Please notice that we encourage you to read our tutorials and learn more about
 [SpeechBrain](https://speechbrain.github.io).
 
-### Transcribing your own audio files (in Hindi)
+### Transcribing your own audio files (in Arabic)
 
 ```python
 
 from speechbrain.pretrained import WhisperASR
 
-asr_model = WhisperASR.from_hparams(source="speechbrain/asr-whisper-large-v2-commonvoice-hi", savedir="pretrained_models/asr-whisper-large-v2-commonvoice-hi")
-asr_model.transcribe_file("speechbrain/asr-whisper-large-v2-commonvoice-hi/example-hi.mp3")
+asr_model = WhisperASR.from_hparams(source="speechbrain/asr-whisper-medium-commonvoice-ar", savedir="pretrained_models/asr-whisper-medium-commonvoice-ar")
+asr_model.transcribe_file("speechbrain/asr-whisper-lmedium-commonvoice-ar/example-ar.mp3")
 
 
 ```
@@ -103,7 +103,7 @@ pip install -e .
 3. Run Training:
 ```bash
 cd recipes/CommonVoice/ASR/transformer/
-python train_with_whisper.py hparams/train_hi_hf_whisper.yaml --data_folder=your_data_folder
+python train_with_whisper.py hparams/train_ar_hf_whisper.yaml --data_folder=your_data_folder
 ```
 
 You can find our training results (models, logs, etc) [here](https://drive.google.com/drive/folders/11PKCsyIE703mmDv6n6n_UnD0bUgMPbg_?usp=share_link).