Update README.md

README.md

@@ -1,6 +1,6 @@
 ---
 language:
-- de
+- en
 thumbnail: null
 pipeline_tag: automatic-speech-recognition
 tags:
@@ -10,36 +10,36 @@ tags:
 - Transformer
 license: apache-2.0
 datasets:
-- commonvoice
+- commonvoice.14.0
 metrics:
 - wer
 - cer
 model-index:
-- name: asr-wav2vec2-commonvoice-de
+- name: asr-wav2vec2-commonvoice-14-en
   results:
   - task:
       name: Automatic Speech Recognition
       type: automatic-speech-recognition
     dataset:
-      name: CommonVoice Corpus 10.0/ (German)
-      type: mozilla-foundation/common_voice_10_1
-      config: de
+      name: CommonVoice Corpus 14.0/ (English)
+      type: mozilla-foundation/common_voice_14.0
+      config: en
       split: test
       args:
-        language: de
+        language: en
     metrics:
     - name: Test WER
       type: wer
-      value: '9.54'
+      value: '16.68'
 ---
 
 <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>
 <br/><br/>
 
-# wav2vec 2.0 with CTC trained on CommonVoice German (No LM)
+# wav2vec 2.0 with CTC trained on CommonVoice English (No LM)
 
 This repository provides all the necessary tools to perform automatic speech
-recognition from an end-to-end system pretrained on CommonVoice (German Language) within
+recognition from an end-to-end system pretrained on CommonVoice (English Language) within
 SpeechBrain. For a better experience, we encourage you to learn more about
 [SpeechBrain](https://speechbrain.github.io).
 
@@ -47,14 +47,14 @@ The performance of the model is the following:
 
 | Release | Test CER | Test WER | GPUs |
 |:-------------:|:--------------:|:--------------:| :--------:|
-| 16-08-22 | 2.40 | 9.54 | 1xRTXA6000 48GB |
+| 15-08-23 | 7.92  | 16.86  | 1xV100 32GB |
 
 ## Pipeline description
 
 This ASR system is composed of 2 different but linked blocks:
-- Tokenizer (char) that transforms words into chars and trained with
-the train transcriptions (train.tsv) of CommonVoice (DE).  
-- Acoustic model (wav2vec2.0 + CTC). A pretrained wav2vec 2.0 model ([wav2vec2-large-xlsr-53-german](https://huggingface.co/facebook/wav2vec2-large-xlsr-53-german)) is combined with two DNN layers and finetuned on CommonVoice DE. 
+- Tokenizer (unigram) that transforms words into unigrams and trained with
+the train transcriptions (train.tsv) of CommonVoice (en).  
+- Acoustic model (wav2vec2.0 + CTC). A pretrained wav2vec 2.0 model ([wav2vec2-large-lv60](https://huggingface.co/facebook/wav2vec2-large-lv60)) is combined with two DNN layers and finetuned on CommonVoice DE. 
 The obtained final acoustic representation is given to the CTC decoder.
 
 The system is trained with recordings sampled at 16kHz (single channel).
@@ -71,13 +71,13 @@ 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 German)
+### Transcribing your own audio files (in English)
 
 ```python
 from speechbrain.pretrained import EncoderASR
 
-asr_model = EncoderASR.from_hparams(source="speechbrain/asr-wav2vec2-commonvoice-de", savedir="pretrained_models/asr-wav2vec2-commonvoice-de")
-asr_model.transcribe_file("speechbrain/asr-wav2vec2-commonvoice-de/example-de.wav")
+asr_model = EncoderASR.from_hparams(source="speechbrain/asr-wav2vec2-commonvoice-14-en", savedir="pretrained_models/asr-wav2vec2-commonvoice-14-en")
+asr_model.transcribe_file("speechbrain/asr-wav2vec2-commonvoice-14-en/example-en.wav")
 
 ```
 ### Inference on GPU