Performance-Efficiency Trade-offs in Unsupervised Pre-training for Speech Recognition

Related tags

Text Data & NLPsew
Overview

SEW (Squeezed and Efficient Wav2vec)

made-with-python License: MIT

The repo contains the code of the paper "Performance-Efficiency Trade-offs in Unsupervised Pre-training for Speech Recognition" by Felix Wu, Kwangyoun Kim, Jing Pan, Kyu Han, Kilian Q Weinberger, and Yoav Artzi.

Model Checkpoints

Unsupervisedly Pre-trained on LibriSpeech 960h

Model Pre-training updates Dataset Model
W2V2-tiny 100K Librispeech 960h download
W2V2-small 100K Librispeech 960h download
W2V2-mid 100K Librispeech 960h download
W2V2-base 100K Librispeech 960h download
SEW-tiny 100K Librispeech 960h download
SEW-small 100K Librispeech 960h download
SEW-mid 100K Librispeech 960h download
SEW-D-tiny 100K Librispeech 960h download
SEW-D-small 100K Librispeech 960h download
SEW-D-mid 100K Librispeech 960h download
SEW-D-mid (k127) 100K Librispeech 960h download
SEW-D-base 100K Librispeech 960h download
SEW-D-base+ 100K Librispeech 960h download
SEW-D-mid 400K Librispeech 960h download
SEW-D-mid (k127) 400K Librispeech 960h download
SEW-D-base+ 400K Librispeech 960h download

ASR model fine-tuned on LibriSpeech train-clean 100h

Model Pre-training updates Finetuning split Model
SEW-tiny 100K 100h download
SEW-D-tiny 100K 100h download
SEW-D-mid 400K 100h download
SEW-D-mid (k127) 400K 100h download
SEW-D-base+ 400K 100h download

Usage

Dependencies

The code is tested with fairseq commit 05255f9, deberta commit bf17ca4 and the following packages.

torch==1.8.0
torchaudio==0.8.0
tqdm==4.49.0
Hydra==2.5
hydra-core==1.0.4
fvcore==0.1.5.post20210330
omegaconf==2.0.5
einops==0.3.0
fire==0.2.1

Apex

Please install NVIDIA's apex with

git clone https://github.com/NVIDIA/apex
cd apex
pip install -v --no-cache-dir --global-option="--cpp_ext" --global-option="--cuda_ext" \
  --global-option="--deprecated_fused_adam" --global-option="--xentropy" \
  --global-option="--fast_multihead_attn" ./

wav2letter decoder

Currently, we are decoding with wav2letter v0.2 python binding at commit 96f5f9d Please install the python binding here https://github.com/flashlight/wav2letter/tree/96f5f9d3b41e01af0a031ee0d2604acd9ef3b1b0/bindings/python The newest commit d5a93f0 in v0.2 branch leads to worse WER for wav2vec 2.0 baselines.

Installation

git clone https://github.com/asappresearch/sew.git
cd sew 
pip install -e .

Pre-training

Pre-training SEW models

Run the following command where $model_size can be tiny, small, or mid, and $ngpu is tne number of GPUs you want to use.

bash scripts/pt-sew.sh $model_size $ngpu

Pre-training SEW-D models

bash scripts/pt-sew-d.sh $model_size $ngpu

where $model_size can be tiny, small, mid, mid-k127, base, or base+.

Fine-tuning

Run the following script to fine-tune a model with the hyperparameters from wav2vec 2.0.

bash scripts/ft-model.sh $pre_trained_model $split $ngpu

where $pre_trained_model can be either a W2V2, SEW, or a SEW-D model checkpoint and $split can be 10m, 1h, 10h, or 100h.

Here we also provide a set of hyperparameters which sets all dropouts the same as the pre-training stage, and we found it to be more stable.

bash scripts/ft-model-stable.sh $pre_trained_model $split $ngpu

If you see out of GPU memory error, please scale down the dataset.max_tokens and scale up the optimization.update_freq in scripts/ft-model.sh. For example modifying these lines

  dataset.max_tokens=3200000 \
  optimization.update_freq="[$((8 / $ngpu))]" \

to

  dataset.max_tokens=1600000 \
  optimization.update_freq="[$((16 / $ngpu))]" \

which reduces the batch size and increases the gradient accumulation steps in order to use less GPU memory.

Evaluation

  1. Please run this script to prepare the official LibriSpeech 4-gram language model.
bash scripts/prepare_librispeech_lm.sh $kenlm_build_bin

where $kenlm_build_bin is the folder that contains the KenLM build_binary executable file (e.g. /home/user/kenlm/build/bin).

  1. Then run this script to evaluate a pre-trained ASR model
python tools/eval_w2v.py tunelm --subsets '["dev-clean", "dev-other", "test-clean", "test-other"]' --model $asr_checkpoint
You might also like...
Neural building blocks for speaker diarization: speech activity detection, speaker change detection, overlapped speech detection, speaker embedding
Neural building blocks for speaker diarization: speech activity detection, speaker change detection, overlapped speech detection, speaker embedding

⚠️ Checkout develop branch to see what is coming in pyannote.audio 2.0: a much smaller and cleaner codebase Python-first API (the good old pyannote-au

PyTorch implementation of Microsoft's text-to-speech system FastSpeech 2: Fast and High-Quality End-to-End Text to Speech.
PyTorch implementation of Microsoft's text-to-speech system FastSpeech 2: Fast and High-Quality End-to-End Text to Speech.

An implementation of Microsoft's "FastSpeech 2: Fast and High-Quality End-to-End Text to Speech"

Simple Speech to Text, Text to Speech

Simple Speech to Text, Text to Speech 1. Download Repository Opsi 1 Download repository ini, extract di lokasi yang diinginkan Opsi 2 Jika sudah famil

Code for ACL 2022 main conference paper "STEMM: Self-learning with Speech-text Manifold Mixup for Speech Translation".

STEMM: Self-learning with Speech-Text Manifold Mixup for Speech Translation This is a PyTorch implementation for the ACL 2022 main conference paper ST

Unsupervised intent recognition

INTENT author: steeve LAQUITAINE description: deployment pattern: currently batch only Setup & run git clone https://github.com/slq0/intent.git bash

Implementaion of our ACL 2022 paper Bridging the Data Gap between Training and Inference for Unsupervised Neural Machine Translation

Bridging the Data Gap between Training and Inference for Unsupervised Neural Machine Translation This is the implementaion of our paper: Bridging the

PhoNLP: A BERT-based multi-task learning toolkit for part-of-speech tagging, named entity recognition and dependency parsing
PhoNLP: A BERT-based multi-task learning toolkit for part-of-speech tagging, named entity recognition and dependency parsing

PhoNLP is a multi-task learning model for joint part-of-speech (POS) tagging, named entity recognition (NER) and dependency parsing. Experiments on Vietnamese benchmark datasets show that PhoNLP produces state-of-the-art results, outperforming a single-task learning approach that fine-tunes the pre-trained Vietnamese language model PhoBERT for each task independently.

Bidirectional LSTM-CRF and ELMo for Named-Entity Recognition, Part-of-Speech Tagging and so on.
Bidirectional LSTM-CRF and ELMo for Named-Entity Recognition, Part-of-Speech Tagging and so on.

anaGo anaGo is a Python library for sequence labeling(NER, PoS Tagging,...), implemented in Keras. anaGo can solve sequence labeling tasks such as nam

Bidirectional LSTM-CRF and ELMo for Named-Entity Recognition, Part-of-Speech Tagging and so on.
Bidirectional LSTM-CRF and ELMo for Named-Entity Recognition, Part-of-Speech Tagging and so on.

anaGo anaGo is a Python library for sequence labeling(NER, PoS Tagging,...), implemented in Keras. anaGo can solve sequence labeling tasks such as nam

Comments
  • 8000 sample rate audio

    8000 sample rate audio

    Hello there,

    I'm trying to train on 8000 Hz sample rate audio dataset. Is it enough to simply add task.sample_rate=8000 to the fairseq command or there are additional config changes that I should make?

    I would much appreciate any advice

    Thank you

    opened by Mega4alik 0
  • How to train using not English Languages

    How to train using not English Languages

    Hi! Thank you for the awesome model!

    We are very interested in your project and we try to use the sew for Japanese Language. When we train the model, should we use these scripts? Thanks! https://github.com/asappresearch/sew/tree/master/scripts

    opened by jigenji 1
  • :bug: Fix padding mask calculation

    :bug: Fix padding mask calculation

    This PR updates the padding mask calculation to be the same as the one in the reference Wav2Vec2 implementation (same commit as listed in SEW's README): https://github.com/pytorch/fairseq/blob/05255f96410e5b1eaf3bf59b767d5b4b7e2c3a35/fairseq/models/wav2vec/wav2vec2.py#L477

    For more details on how and why it was fixed in fairseq, check out this PR by @patrickvonplaten https://github.com/pytorch/fairseq/pull/3228

    opened by anton-l 0
Releases(v0.0.1)
Owner
ASAPP Research
AI for Enterprise
ASAPP Research
Generate custom detailed survey paper with topic clustered sections and proper citations, from just a single query in just under 30 mins !!

Auto-Research A no-code utility to generate a detailed well-cited survey with topic clustered sections (draft paper format) and other interesting arti

Sidharth Pal 20 Dec 14, 2022
Club chatbot

Chatbot Club chatbot Instructions to get the Chatterbot working Step 1. First make sure you are using a version of Python 3 or newer. To check your ve

5 Mar 07, 2022
Code Generation using a large neural network called GPT-J

CodeGenX is a Code Generation system powered by Artificial Intelligence! It is delivered to you in the form of a Visual Studio Code Extension and is Free and Open-source!

DeepGenX 389 Dec 31, 2022
Contact Extraction with Question Answering.

contactsQA Extraction of contact entities from address blocks and imprints with Extractive Question Answering. Goal Input: Dr. Max Mustermann Hauptstr

Jan 2 Apr 20, 2022
Script and models for clustering LAION-400m CLIP embeddings.

clustering-laion400m Script and models for clustering LAION-400m CLIP embeddings. Models were fit on the first million or so image embeddings. A subje

Peter Baylies 22 Oct 04, 2022
🤗 The largest hub of ready-to-use NLP datasets for ML models with fast, easy-to-use and efficient data manipulation tools

🤗 The largest hub of ready-to-use NLP datasets for ML models with fast, easy-to-use and efficient data manipulation tools

Hugging Face 15k Jan 02, 2023
Persian Bert For Long-Range Sequences

ParsBigBird: Persian Bert For Long-Range Sequences The Bert and ParsBert algorithms can handle texts with token lengths of up to 512, however, many ta

Sajjad Ayoubi 63 Dec 14, 2022
Scene Text Retrieval via Joint Text Detection and Similarity Learning

This is the code of "Scene Text Retrieval via Joint Text Detection and Similarity Learning". For more details, please refer to our CVPR2021 paper.

79 Nov 29, 2022
nlp-tutorial is a tutorial for who is studying NLP(Natural Language Processing) using Pytorch

nlp-tutorial is a tutorial for who is studying NLP(Natural Language Processing) using Pytorch. Most of the models in NLP were implemented with less than 100 lines of code.(except comments or blank li

Tae-Hwan Jung 11.9k Jan 08, 2023
CoSENT 比Sentence-BERT更有效的句向量方案

CoSENT 比Sentence-BERT更有效的句向量方案

苏剑林(Jianlin Su) 201 Dec 12, 2022
Code from the paper "High-Performance Brain-to-Text Communication via Handwriting"

Code from the paper "High-Performance Brain-to-Text Communication via Handwriting"

Francis R. Willett 305 Dec 22, 2022
Common Voice Dataset explorer

Common Voice Dataset Explorer Common Voice Dataset is by Mozilla Made during huggingface finetuning week Usage pip install -r requirements.txt streaml

Ceyda Cinarel 22 Nov 16, 2022
Deduplication is the task to combine different representations of the same real world entity.

Deduplication is the task to combine different representations of the same real world entity. This package implements deduplication using active learning. Active learning allows for rapid training wi

63 Nov 17, 2022
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

342 Nov 21, 2022
GSoC'2021 | TensorFlow implementation of Wav2Vec2

GSoC'2021 | TensorFlow implementation of Wav2Vec2

Vasudev Gupta 73 Nov 28, 2022
ChainKnowledgeGraph, 产业链知识图谱包括A股上市公司、行业和产品共3类实体

ChainKnowledgeGraph, 产业链知识图谱包括A股上市公司、行业和产品共3类实体,包括上市公司所属行业关系、行业上级关系、产品上游原材料关系、产品下游产品关系、公司主营产品、产品小类共6大类。 上市公司4,654家,行业511个,产品95,559条、上游材料56,824条,上级行业480条,下游产品390条,产品小类52,937条,所属行业3,946条。

liuhuanyong 415 Jan 06, 2023
This repository details the steps in creating a Part of Speech tagger using Trigram Hidden Markov Models and the Viterbi Algorithm without using external libraries.

POS-Tagger This repository details the creation of a Part-of-Speech tagger using Trigram Hidden Markov Models to predict word tags in a word sequence.

Raihan Ahmed 1 Dec 09, 2021
Blazing fast language detection using fastText model

Luga A blazing fast language detection using fastText's language models Luga is a Swahili word for language. fastText provides a blazing fast language

Prayson Wilfred Daniel 18 Dec 20, 2022
💥 Fast State-of-the-Art Tokenizers optimized for Research and Production

Provides an implementation of today's most used tokenizers, with a focus on performance and versatility. Main features: Train new vocabularies and tok

Hugging Face 6.2k Dec 31, 2022
Simple text to phones converter for multiple languages

Phonemizer -- foʊnmaɪzɚ The phonemizer allows simple phonemization of words and texts in many languages. Provides both the phonemize command-line tool

CoML 762 Dec 29, 2022