Upload README.md

README.md

@@ -1,6 +1,6 @@
 ---
 language:
-- fr
+- en
 thumbnail: null
 pipeline_tag: automatic-speech-recognition
 tags:
@@ -8,39 +8,38 @@ tags:
 - pytorch
 - speechbrain
 - Transformer
-- hf-asr-leaderboard
 license: apache-2.0
 datasets:
-- commonvoice
+- commonvoice.14.0
 metrics:
 - wer
 - cer
 model-index:
-- name: asr-wav2vec2-commonvoice-fr
+- name: asr-wav2vec2-commonvoice-14-en
   results:
   - task:
       name: Automatic Speech Recognition
       type: automatic-speech-recognition
     dataset:
-      name: CommonVoice 6.1 (French)
-      type: mozilla-foundation/common_voice_6_1
-      config: fr
+      name: CommonVoice Corpus 14.0 (English)
+      type: mozilla-foundation/common_voice_14.0
+      config: en
       split: test
       args:
-        language: fr
+        language: en
     metrics:
     - name: Test WER
       type: wer
-      value: '9.96'
+      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/Attention trained on CommonVoice French (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 (French 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).
 
@@ -48,15 +47,15 @@ The performance of the model is the following:
 
 | Release | Test CER | Test WER | GPUs |
 |:-------------:|:--------------:|:--------------:| :--------:|
-| 24-08-21 | 3.19 | 9.96 | 2xV100 32GB |
+| 15-08-23 | 7.92  | 16.86  | 1xV100 32GB |
 
 ## Pipeline description
 
 This ASR system is composed of 2 different but linked blocks:
-- Tokenizer (unigram) that transforms words into subword units and trained with
-the train transcriptions (train.tsv) of CommonVoice (FR).
-- Acoustic model (wav2vec2.0 + CTC). A pretrained wav2vec 2.0 model ([LeBenchmark/wav2vec2-FR-7K-large](https://huggingface.co/LeBenchmark/wav2vec2-FR-7K-large)) is combined with two DNN layers and finetuned on CommonVoice FR.
-The obtained final acoustic representation is given to the CTC greedy decoder.
+- 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).
 The code will automatically normalize your audio (i.e., resampling + mono channel selection) when calling *transcribe_file* if needed.
@@ -72,18 +71,21 @@ 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 French)
+### Transcribing your own audio files (in English)
 
 ```python
 from speechbrain.pretrained import EncoderASR
 
-asr_model = EncoderASR.from_hparams(source="speechbrain/asr-wav2vec2-commonvoice-fr", savedir="pretrained_models/asr-wav2vec2-commonvoice-fr")
-asr_model.transcribe_file('speechbrain/asr-wav2vec2-commonvoice-fr/example-fr.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
 To perform inference on the GPU, add  `run_opts={"device":"cuda"}`  when calling the `from_hparams` method.
 
+## Parallel Inference on a Batch
+Please, [see this Colab notebook](https://colab.research.google.com/drive/1hX5ZI9S4jHIjahFCZnhwwQmFoGAi3tmu?usp=sharing) to figure out how to transcribe in parallel a batch of input sentences using a pre-trained model.
+
 ### Training
 The model was trained with SpeechBrain.
 To train it from scratch follow these steps:
@@ -101,30 +103,32 @@ pip install -e .
 3. Run Training:
 ```bash
 cd recipes/CommonVoice/ASR/CTC/
-python train_with_wav2vec.py hparams/train_fr_with_wav2vec.yaml --data_folder=your_data_folder
+python train_with_wav2vec.py hparams/train_en_with_wav2vec.yaml --data_folder=your_data_folder
 ```
 
-You can find our training results (models, logs, etc) [here](https://drive.google.com/drive/folders/1T9DfdZwcNI9CURxhLCi8GA5JVz8adiY8?usp=sharing).
+You can find our training results (models, logs, etc) [here](https://www.dropbox.com/sh/ch10cnbhf1faz3w/AACdHFG65LC6582H0Tet_glTa?dl=0).
 
 ### Limitations
 The SpeechBrain team does not provide any warranty on the performance achieved by this model when used on other datasets.
 
-#### Referencing SpeechBrain
 
-```
-@misc{SB2021,
-    author = {Ravanelli, Mirco and Parcollet, Titouan and Rouhe, Aku and Plantinga, Peter and Rastorgueva, Elena and Lugosch, Loren and Dawalatabad, Nauman and Ju-Chieh, Chou and Heba, Abdel and Grondin, Francois and Aris, William and Liao, Chien-Feng and Cornell, Samuele and Yeh, Sung-Lin and Na, Hwidong and Gao, Yan and Fu, Szu-Wei and Subakan, Cem and De Mori, Renato and Bengio, Yoshua },
-    title = {SpeechBrain},
-    year = {2021},
-    publisher = {GitHub},
-    journal = {GitHub repository},
-    howpublished = {\\\\url{https://github.com/speechbrain/speechbrain}},
-  }
-```
+# **About SpeechBrain**
+- Website: https://speechbrain.github.io/
+- Code: https://github.com/speechbrain/speechbrain/
+- HuggingFace: https://huggingface.co/speechbrain/
 
-#### About SpeechBrain
-SpeechBrain is an open-source and all-in-one speech toolkit. It is designed to be simple, extremely flexible, and user-friendly. Competitive or state-of-the-art performance is obtained in various domains.
 
-Website: https://speechbrain.github.io/
+# **Citing SpeechBrain**
+Please, cite SpeechBrain if you use it for your research or business.
 
-GitHub: https://github.com/speechbrain/speechbrain
+```bibtex
+@misc{speechbrain,
+  title={{SpeechBrain}: A General-Purpose Speech Toolkit},
+  author={Mirco Ravanelli and Titouan Parcollet and Peter Plantinga and Aku Rouhe and Samuele Cornell and Loren Lugosch and Cem Subakan and Nauman Dawalatabad and Abdelwahab Heba and Jianyuan Zhong and Ju-Chieh Chou and Sung-Lin Yeh and Szu-Wei Fu and Chien-Feng Liao and Elena Rastorgueva and François Grondin and William Aris and Hwidong Na and Yan Gao and Renato De Mori and Yoshua Bengio},
+  year={2021},
+  eprint={2106.04624},
+  archivePrefix={arXiv},
+  primaryClass={eess.AS},
+  note={arXiv:2106.04624}
+}
+```