Update README.md

README.md

@@ -1,6 +1,6 @@
 ---
 language:
-- ar
+- it
 thumbnail: null
 pipeline_tag: automatic-speech-recognition
 tags:
@@ -16,22 +16,22 @@ metrics:
 - wer
 - cer
 model-index:
-- name: asr-whisper-medium-commonvoice-ar
+- name: asr-whisper-medium-commonvoice-it
   results:
   - task:
       name: Automatic Speech Recognition
       type: automatic-speech-recognition
     dataset:
-      name: CommonVoice 10.0 (Arabic)
+      name: CommonVoice 10.0 (Italian)
       type: mozilla-foundation/common_voice_14_0
-      config: ar
+      config: it
       split: test
       args:
-        language: ar
+        language: it
     metrics:
     - name: Test WER
       type: wer
-      value: '14.82'
+      value: '8.26'
 ---
 
 <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>
@@ -40,7 +40,7 @@ model-index:
 # 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 (Arabic Language) within
+recognition from an end-to-end whisper model fine-tuned on CommonVoice (Italian 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 |
 |:-------------:|:--------------:|:--------------:| :--------:|
-| 1-08-23 | 4.95 |  14.82 | 1xV100 32GB |
+| 1-08-23 | 2.42 |  8.26 | 1xV100 32GB |
 
 ## Pipeline description
 
 This ASR system is composed of whisper encoder-decoder blocks:
 - The pretrained whisper-medium encoder is frozen.
 - The pretrained Whisper tokenizer is used.
-- A pretrained Whisper-medium decoder ([openai/whisper-medium](https://huggingface.co/openai/whisper-medium)) is finetuned on CommonVoice ar.
+- A pretrained Whisper-medium decoder ([openai/whisper-medium](https://huggingface.co/openai/whisper-medium)) is finetuned on CommonVoice it.
 The obtained final acoustic representation is given to the greedy decoder. 
 
 The system is trained with recordings sampled at 16kHz (single channel).
@@ -72,14 +72,14 @@ 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 Arabic)
+### Transcribing your own audio files (in Italian)
 
 ```python
 
 from speechbrain.pretrained import WhisperASR
 
-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")
+asr_model = WhisperASR.from_hparams(source="speechbrain/asr-whisper-medium-commonvoice-it", savedir="pretrained_models/asr-whisper-medium-commonvoice-it")
+asr_model.transcribe_file("speechbrain/asr-whisper-lmedium-commonvoice-it/example-it.mp3")
 
 
 ```
@@ -103,7 +103,7 @@ pip install -e .
 3. Run Training:
 ```bash
 cd recipes/CommonVoice/ASR/transformer/
-python train_with_whisper.py hparams/train_ar_hf_whisper.yaml --data_folder=your_data_folder
+python train_with_whisper.py hparams/train_it_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).
@@ -129,4 +129,4 @@ SpeechBrain is an open-source and all-in-one speech toolkit. It is designed to b
 
 Website: https://speechbrain.github.io/
 
-GitHub: https://github.com/speechbrain/speechbrain
+GitHub: https://github.com/speechbrain/speechbrain