Explore different way to mix speech model(wav2vec2, hubert) and nlp model(BART,T5,GPT) together

Related tags

Text Data & NLPSpeechMix
Overview

SpeechMix

Explore different way to mix speech model(wav2vec2, hubert) and nlp model(BART,T5,GPT) together.

Introduction

For the same input:

from datasets import load_dataset
import soundfile as sf


# define function to read in sound file
def map_to_array(batch):
    speech, _ = sf.read(batch["file"])
    batch["speech"] = speech
    return batch


# load dummy dataset and read soundfiles
ds = load_dataset("patrickvonplaten/librispeech_asr_dummy", "clean", split="validation")
ds = ds.map(map_to_array)

transcript = ds['text'][0]
speech = ds["speech"][0]

Speech encoder NLP decoder

model = SpeechMixED("facebook/wav2vec2-base-960h", "facebook/bart-large")

transcript_tensor = model.tokenizer(transcript, return_tensors="pt").input_ids
speech_tensor = model.processor(speech, return_tensors="pt").input_values

model(speech_tensor, transcript_tensor)

Speech encoder NLP decoder only fine-tune on cross attention/projection/decoder embedding

model = SpeechMixED("facebook/wav2vec2-base-960h", "facebook/bart-large", ftl=True)

transcript_tensor = model.tokenizer(transcript, return_tensors="pt").input_ids
speech_tensor = model.processor(speech, return_tensors="pt").input_values

model(speech_tensor, transcript_tensor)

Speech encoder NLP encoder decoder

model = SpeechMixEED("facebook/wav2vec2-base-960h", "facebook/bart-large")

transcript_tensor = model.tokenizer(transcript, return_tensors="pt").input_ids
speech_tensor = model.processor(speech, return_tensors="pt").input_values

model(speech_tensor, transcript_tensor)

Speech encoder NLP encoder decoder only fine-tune on layer norm and attention

model = SpeechMixEED("facebook/wav2vec2-base-960h", "facebook/bart-large", lna=True)

transcript_tensor = model.tokenizer(transcript, return_tensors="pt").input_ids
speech_tensor = model.processor(speech, return_tensors="pt").input_values

model(speech_tensor, transcript_tensor)

Speech encoder NLP encoder decoder only fine-tune on speech encoder

model = SpeechMixEED("facebook/wav2vec2-base-960h", "facebook/bart-large", fne=True)

transcript_tensor = model.tokenizer(transcript, return_tensors="pt").input_ids
speech_tensor = model.processor(speech, return_tensors="pt").input_values

model(speech_tensor, transcript_tensor)

Installation

pip install

pip install speechmix

Build from source

git clone and cd into this project.

pip install -e .
Owner
Eric Lam
NLP researcher, Data scientist and computer science engineer.
Eric Lam
GitHub Repository
Code for EmBERT, a transformer model for embodied, language-guided visual task completion.

Code for EmBERT, a transformer model for embodied, language-guided visual task completion.

41 Jan 03, 2023
FastFormers - highly efficient transformer models for NLU

FastFormers FastFormers provides a set of recipes and methods to achieve highly efficient inference of Transformer models for Natural Language Underst

Microsoft 678 Jan 05, 2023
CoSENT、STS、SentenceBERT

CoSENT_Pytorch 比Sentence-BERT更有效的句向量方案

102 Dec 07, 2022
This is a Python binding to the tokenizer Ucto. Tokenisation is one of the first step in almost any Natural Language Processing task, yet it is not always as trivial a task as it appears to be. This binding makes the power of the ucto tokeniser available to Python. Ucto itself is regular-expression based, extensible, and advanced tokeniser written in C++ (http://ilk.uvt.nl/ucto).

Ucto for Python This is a Python binding to the tokeniser Ucto. Tokenisation is one of the first step in almost any Natural Language Processing task,

Maarten van Gompel 27 Dec 14, 2022
LOT: A Benchmark for Evaluating Chinese Long Text Understanding and Generation

LOT: A Benchmark for Evaluating Chinese Long Text Understanding and Generation Tasks | Datasets | LongLM | Baselines | Paper Introduction LOT is a ben

46 Dec 28, 2022
A website which allows you to play with the GPT-2 transformer

transformers A website which allows you to play with the GPT-2 model Built with ❤️ by raphtlw Table of contents Model Setup About Contributors Model T

raphtlw 2 Jan 27, 2022
This repository contains the code, models and datasets discussed in our paper "Few-Shot Question Answering by Pretraining Span Selection"

Splinter This repository contains the code, models and datasets discussed in our paper "Few-Shot Question Answering by Pretraining Span Selection", to

Ori Ram 88 Dec 31, 2022
Code and datasets for our paper "PTR: Prompt Tuning with Rules for Text Classification"

PTR Code and datasets for our paper "PTR: Prompt Tuning with Rules for Text Classification" If you use the code, please cite the following paper: @art

THUNLP 118 Dec 30, 2022
GPT-Code-Clippy (GPT-CC) is an open source version of GitHub Copilot, a language model

GPT-Code-Clippy (GPT-CC) is an open source version of GitHub Copilot, a language model -- based on GPT-3, called GPT-Codex -- that is fine-tuned on publicly available code from GitHub.

Nathan Cooper 2.3k Jan 01, 2023
T‘rex Park is a Youzan sponsored project. Offering Chinese NLP and image models pretrained from E-commerce datasets

T‘rex Park is a Youzan sponsored project. Offering Chinese NLP and image models pretrained from E-commerce datasets (product titles, images, comments, etc.).

55 Nov 22, 2022
L3Cube-MahaCorpus a Marathi monolingual data set scraped from different internet sources.

L3Cube-MahaCorpus L3Cube-MahaCorpus a Marathi monolingual data set scraped from different internet sources. We expand the existing Marathi monolingual

21 Dec 17, 2022
Fully featured implementation of Routing Transformer

Routing Transformer A fully featured implementation of Routing Transformer. The paper proposes using k-means to route similar queries / keys into the

Phil Wang 246 Jan 02, 2023
Linear programming solver for paper-reviewer matching and mind-matching

Paper-Reviewer Matcher A python package for paper-reviewer matching algorithm based on topic modeling and linear programming. The algorithm is impleme

Titipat Achakulvisut 66 Jul 05, 2022
AutoGluon: AutoML for Text, Image, and Tabular Data

AutoML for Text, Image, and Tabular Data AutoGluon automates machine learning tasks enabling you to easily achieve strong predictive performance in yo

Amazon Web Services - Labs 5.2k Dec 29, 2022
Open-Source Toolkit for End-to-End Speech Recognition leveraging PyTorch-Lightning and Hydra.

OpenSpeech provides reference implementations of various ASR modeling papers and three languages recipe to perform tasks on automatic speech recogniti

Soohwan Kim 26 Dec 14, 2022
Korean stereoypte detector with TUNiB-Electra and K-StereoSet

Korean Stereotype Detector Korean stereotype sentence classifier using K-StereoSet with TUNiB-Electra Web demo you can test this model easily in demo

Sae_Chan_Oh 11 Feb 18, 2022
Transcribing audio files using Hugging Face's implementation of Wav2Vec2 + "chain-linking" NLP tasks to combine speech-to-text with downstream tasks like translation and summarisation.

PART 2: CHAIN LINKING AUDIO-TO-TEXT NLP TASKS 2A: TRANSCRIBE-TRANSLATE-SENTIMENT-ANALYSIS In notebook3.0, I demo a simple workflow to: transcribe a lo

Chua Chin Hon 30 Jul 13, 2022
Pretty-doc - Composable text objects with python

pretty-doc from __future__ import annotations from dataclasses import dataclass

Taine Zhao 2 Jan 17, 2022
Final Project for the Intel AI Readiness Boot Camp NLP (Jan)

NLP Boot Camp (Jan) Synopsis Full Name: Prameya Mohanty Name of your School: Delhi Public School, Rourkela Class: VIII Title of the Project: iTransect

TheCodingHub 1 Feb 01, 2022
A multi-voice TTS system trained with an emphasis on quality

TorToiSe Tortoise is a text-to-speech program built with the following priorities: Strong multi-voice capabilities. Highly realistic prosody and inton

James Betker 2.1k Jan 01, 2023