CRDNN with CTC/Attention trained on CommonVoice 10.0 German and RNNLM trained (with 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 SpeechBrain. For a better experience, we encourage you to learn more about SpeechBrain. The performance of the model is the following (after 25 epochs):

Release	Test CER	Test WER	GPUs
15.08.23	2.85	7.92	1xRTXA6000 48GB

Pipeline description

This ASR system is composed with 3 different but linked blocks:

Tokenizer (unigram) that transforms words into subword units and trained with the train transcriptions of LibriSpeech.
Neural language model (RNNLM) trained on the 17M sentences combining Tuda-De2 (8M sents), Leipzig news corpus (9M sents), and train transcripts of the CommonVoice corpus.
Acoustic model (CRDNN + CTC/Attention). The CRDNN architecture is made of N blocks of convolutional neural networks with normalisation and pooling on the frequency domain. Then, a bidirectional LSTM is connected to a final DNN to obtain the final acoustic representation that is given to the CTC and attention decoders.

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.

Install SpeechBrain

First of all, please install SpeechBrain with the following command:

pip install speechbrain

Please notice that we encourage you to read our tutorials and learn more about SpeechBrain.

Transcribing your own audio files (in German)

from speechbrain.pretrained import EncoderDecoderASR
asr_model = EncoderDecoderASR.from_hparams(source="sangeet2020/asr-crdnn-rnnlm-commonvoice-10.0-de", savedir="pretrained_models/speechbrain/asr-crdnn-rnnlm-commonvoice-10.0-de")
asr_model.transcribe_file("speechbrain/speechbrain/asr-crdnn-rnnlm-commonvoice-10.0-de/example-de.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 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 (986a2175). To train it from scratch follows these steps:

Clone SpeechBrain:

git clone https://github.com/speechbrain/speechbrain/

Install it:

cd speechbrain
pip install -r requirements.txt
pip install -e .

Run Training:

cd recipes/CommonVoice/ASR/seq2seq
python train.py hparams/train_de.yaml --data_folder=your_data_folder

Limitations

The SpeechBrain team does not provide any warranty on the performance achieved by this model when used on other datasets.

About SpeechBrain

Website: https://speechbrain.github.io/
Code: https://github.com/speechbrain/speechbrain/
HuggingFace: https://huggingface.co/speechbrain/

Citing SpeechBrain

Please, cite SpeechBrain if you use it for your research or business.

@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}
}