Transformers Wav2Vec2 + Parlance's CTCDecodeTransformers Wav2Vec2 + Parlance's CTCDecode

Overview

🤗 Transformers Wav2Vec2 + Parlance's CTCDecode

Introduction

This repo shows how 🤗 Transformers can be used in combination with Parlance's ctcdecode & KenLM ngram as a simple way to boost word error rate (WER).

Included is a file to create an ngram with KenLM as well as a simple evaluation script to compare the results of using Wav2Vec2 with ctcdecode + KenLM vs. without using any language model.

Note: The scripts are written to be used on GPU. If you want to use a CPU instead, simply remove all .to("cuda") occurances in eval.py.

Installation

In a first step, one should install KenLM. For Ubuntu, it should be enough to follow the installation steps described here. The installed kenlm folder should be move into this repo for ./create_ngram.py to function correctly. Alternatively, one can also link the lmplz binary file to a lmplz bash command to directly run lmplz instead of ./kenlm/build/bin/lmplz.

Next, some Python dependencies should be installed. Assuming PyTorch is installed, it should be sufficient to run pip install -r requirements.txt.

Run evaluation

Create ngram

In a first step on should create a ngram. E.g. for polish the command would be:

./create_ngram.py --language polish --path_to_ngram polish.arpa

After the language model is created, one should open the file. one should add a The file should have a structure which looks more or less as follows:

\data\        
ngram 1=86586
ngram 2=546387
ngram 3=796581           
ngram 4=843999             
ngram 5=850874              
                                                  
\1-grams:
-5.7532206      
   
       0
0       
         -0.06677356                                                                            
-3.4645514      drugi   -0.2088903
...

   

Now it is very important also add a token to the n-gram so that it can be correctly loaded. You can simple copy the line:

0 -0.06677356

and change to . When doing this you should also inclease ngram by 1. The new ngram should look as follows:

\data\
ngram 1=86587
ngram 2=546387
ngram 3=796581
ngram 4=843999
ngram 5=850874

\1-grams:
-5.7532206      
    
        0
0       
          -0.06677356
0            -0.06677356
-3.4645514      drugi   -0.2088903
...

    

Now the ngram can be correctly used with pyctcdecode

Run eval

Having created the ngram, one can run:

./eval.py --language polish --path_to_ngram polish.arpa

To compare Wav2Vec2 + LM vs. Wav2Vec2 + No LM on polish.

Results

==================================================polish==================================================
polish - No LM - | WER: 0.3069742867206763 | CER: 0.06054530156286364 | Time: 32.37423086166382
polish - With LM - | WER: 0.39526828695550076 | CER: 0.17596985266474516 | Time: 62.017329692840576

I didn't obtain any good results even when trying out a variety of different settings for alpha and beta. Sadly there aren't many examples, tutorials or docs on parlance/ctcdecode so it's hard to find the reason for the problem.

Also tried it out for other languages like Portuguese and Spanish, but no luck there either.

You might also like...
🤗Transformers: State-of-the-art Natural Language Processing for Pytorch and TensorFlow 2.0.
🤗Transformers: State-of-the-art Natural Language Processing for Pytorch and TensorFlow 2.0.

State-of-the-art Natural Language Processing for PyTorch and TensorFlow 2.0 🤗 Transformers provides thousands of pretrained models to perform tasks o

:mag: End-to-End Framework for building natural language search interfaces to data by utilizing Transformers and the State-of-the-Art of NLP. Supporting DPR, Elasticsearch, HuggingFace’s Modelhub and much more!
:mag: End-to-End Framework for building natural language search interfaces to data by utilizing Transformers and the State-of-the-Art of NLP. Supporting DPR, Elasticsearch, HuggingFace’s Modelhub and much more!

Haystack is an end-to-end framework that enables you to build powerful and production-ready pipelines for different search use cases. Whether you want

🛸 Use pretrained transformers like BERT, XLNet and GPT-2 in spaCy

spacy-transformers: Use pretrained transformers like BERT, XLNet and GPT-2 in spaCy This package provides spaCy components and architectures to use tr

spaCy plugin for Transformers , Udify, ELmo, etc.

Camphr - spaCy plugin for Transformers, Udify, Elmo, etc. Camphr is a Natural Language Processing library that helps in seamless integration for a wid

A deep learning-based translation library built on Huggingface transformers

DL Translate A deep learning-based translation library built on Huggingface transformers and Facebook's mBART-Large 💻 GitHub Repository 📚 Documentat

Guide: Finetune GPT2-XL (1.5 Billion Parameters) and GPT-NEO (2.7 B) on a single 16 GB VRAM V100 Google Cloud instance with Huggingface Transformers using DeepSpeed

Guide: Finetune GPT2-XL (1.5 Billion Parameters) and GPT-NEO (2.7 Billion Parameters) on a single 16 GB VRAM V100 Google Cloud instance with Huggingfa

Code for CVPR 2021 paper: Revamping Cross-Modal Recipe Retrieval with Hierarchical Transformers and Self-supervised Learning

Revamping Cross-Modal Recipe Retrieval with Hierarchical Transformers and Self-supervised Learning This is the PyTorch companion code for the paper: A

[Preprint] Escaping the Big Data Paradigm with Compact Transformers, 2021
[Preprint] Escaping the Big Data Paradigm with Compact Transformers, 2021

Compact Transformers Preprint Link: Escaping the Big Data Paradigm with Compact Transformers By Ali Hassani[1]*, Steven Walton[1]*, Nikhil Shah[1], Ab

keras implement of transformers for humans

keras implement of transformers for humans

Owner
Patrick von Platen
Patrick von Platen
GSoC'2021 | TensorFlow implementation of Wav2Vec2

GSoC'2021 | TensorFlow implementation of Wav2Vec2

Vasudev Gupta 73 Nov 28, 2022
Explore different way to mix speech model(wav2vec2, hubert) and nlp model(BART,T5,GPT) together

SpeechMix Explore different way to mix speech model(wav2vec2, hubert) and nlp model(BART,T5,GPT) together. Introduction For the same input: from datas

Eric Lam 31 Nov 7, 2022
Flexible interface for high-performance research using SOTA Transformers leveraging Pytorch Lightning, Transformers, and Hydra.

Flexible interface for high performance research using SOTA Transformers leveraging Pytorch Lightning, Transformers, and Hydra. What is Lightning Tran

Pytorch Lightning 581 Dec 21, 2022
Framework for fine-tuning pretrained transformers for Named-Entity Recognition (NER) tasks

NERDA Not only is NERDA a mesmerizing muppet-like character. NERDA is also a python package, that offers a slick easy-to-use interface for fine-tuning

Ekstra Bladet 141 Dec 30, 2022
KoBART model on huggingface transformers

KoBART-Transformers SKT에서 공개한 KoBART를 편리하게 사용할 수 있게 transformers로 포팅하였습니다. Install (Optional) BartModel과 PreTrainedTokenizerFast를 이용하면 설치하실 필요 없습니다. p

Hyunwoong Ko 58 Dec 7, 2022
Big Bird: Transformers for Longer Sequences

BigBird, is a sparse-attention based transformer which extends Transformer based models, such as BERT to much longer sequences. Moreover, BigBird comes along with a theoretical understanding of the capabilities of a complete transformer that the sparse model can handle.

Google Research 457 Dec 23, 2022
🤗Transformers: State-of-the-art Natural Language Processing for Pytorch and TensorFlow 2.0.

State-of-the-art Natural Language Processing for PyTorch and TensorFlow 2.0 ?? Transformers provides thousands of pretrained models to perform tasks o

Hugging Face 77.3k Jan 3, 2023
:mag: Transformers at scale for question answering & neural search. Using NLP via a modular Retriever-Reader-Pipeline. Supporting DPR, Elasticsearch, HuggingFace's Modelhub...

Haystack is an end-to-end framework for Question Answering & Neural search that enables you to ... ... ask questions in natural language and find gran

deepset 6.4k Jan 9, 2023
🛸 Use pretrained transformers like BERT, XLNet and GPT-2 in spaCy

spacy-transformers: Use pretrained transformers like BERT, XLNet and GPT-2 in spaCy This package provides spaCy components and architectures to use tr

Explosion 1.2k Jan 8, 2023
spaCy plugin for Transformers , Udify, ELmo, etc.

Camphr - spaCy plugin for Transformers, Udify, Elmo, etc. Camphr is a Natural Language Processing library that helps in seamless integration for a wid

null 342 Nov 21, 2022