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

Related tags

Text Data & NLP SpeechMix
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 .
You might also like...
Grading tools for Advanced NLP (11-711)Grading tools for Advanced NLP (11-711)

Grading tools for Advanced NLP (11-711) Installation You'll need docker and unzip to use this repo. For docker, visit the official guide to get starte

Hao Zhu 2 Sep 27, 2022
API for the GPT-J language model ๐Ÿฆœ. Including a FastAPI backend and a streamlit frontend

gpt-j-api ๐Ÿฆœ An API to interact with the GPT-J language model. You can use and test the model in two different ways: Streamlit web app at http://api.v

Vรญctor Gallego 276 Dec 31, 2022
An implementation of model parallel GPT-3-like models on GPUs, based on the DeepSpeed library. Designed to be able to train models in the hundreds of billions of parameters or larger.

GPT-NeoX An implementation of model parallel GPT-3-like models on GPUs, based on the DeepSpeed library. Designed to be able to train models in the hun

EleutherAI 3.1k Jan 8, 2023
Python package to easily retrain OpenAI's GPT-2 text-generating model on new texts
Python package to easily retrain OpenAI's GPT-2 text-generating model on new texts

gpt-2-simple A simple Python package that wraps existing model fine-tuning and generation scripts for OpenAI's GPT-2 text generation model (specifical

Max Woolf 3.1k Jan 7, 2023
Python package to easily retrain OpenAI's GPT-2 text-generating model on new texts
Python package to easily retrain OpenAI's GPT-2 text-generating model on new texts

gpt-2-simple A simple Python package that wraps existing model fine-tuning and generation scripts for OpenAI's GPT-2 text generation model (specifical

Max Woolf 2.5k Feb 17, 2021
Implementation of Token Shift GPT - An autoregressive model that solely relies on shifting the sequence space for mixing

Token Shift GPT Implementation of Token Shift GPT - An autoregressive model that relies solely on shifting along the sequence dimension and feedforwar

Phil Wang 32 Oct 14, 2022
Train GPT-3 model on V100(16GB Mem) Using improved Transformer.
Train GPT-3 model on V100(16GB Mem) Using improved Transformer.

GPT-X using transformer pytorch

Seonghwan Kim 24 Sep 11, 2022
Bot to connect a real Telegram user, simulating responses with OpenAI's davinci GPT-3 model.

AI-BOT Bot to connect a real Telegram user, simulating responses with OpenAI's davinci GPT-3 model.

Thempra 2 Dec 21, 2022
Honor's thesis project analyzing whether the GPT-2 model can more effectively generate free-verse or structured poetry.

gpt2-poetry The following code is for my senior honor's thesis project, under the guidance of Dr. Keith Holyoak at the University of California, Los A

Ashley Kim 2 Jan 9, 2022
Comments
  • Restyle changed eval for time benchmark

    Restyle changed eval for time benchmark

    A duplicate of #4 with additional commits that automatically address incorrect style, created by Restyled.

    :warning: Even though this PR is not a Fork, it contains outside contributions. Please review accordingly.

    Since the original Pull Request was opened as a fork in a contributor's repository, we are unable to create a Pull Request branching from it with only the style fixes.

    The following Restylers made fixes:

    To incorporate these changes, you can either:

    1. Merge this Pull Request instead of the original, or

    2. Ask your contributor to locally incorporate these commits and push them to the original Pull Request

      Expand for example instructions 
      ```console
git remote add upstream https://github.com/voidful/SpeechMix.git
git fetch upstream pull/<this PR number>/head
git merge --ff-only FETCH_HEAD
git push
```

    NOTE: As work continues on the original Pull Request, this process will re-run and update (force-push) this Pull Request with updated style fixes as necessary. If the style is fixed manually at any point (i.e. this process finds no fixes to make), this Pull Request will be closed automatically.

    Sorry if this was unexpected. To disable it, see our documentation.

    opened by restyled-io[bot] 0
Owner
Eric Lam
NLP researcher, Data scientist and computer science engineer.
Eric Lam
GitHub
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 1, 2023
A collection of scripts to preprocess ASR datasets and finetune language-specific Wav2Vec2 XLSR models

wav2vec-toolkit A collection of scripts to preprocess ASR datasets and finetune language-specific Wav2Vec2 XLSR models This repository accompanies the

Anton Lozhkov 29 Oct 23, 2022
GSoC'2021 | TensorFlow implementation of Wav2Vec2

GSoC'2021 | TensorFlow implementation of Wav2Vec2

Vasudev Gupta 73 Nov 28, 2022
Two-stage text summarization with BERT and BART

Two-Stage Text Summarization Description We experiment with a 2-stage summarization model on CNN/DailyMail dataset that combines the ability to filter

Yukai Yang (Alexis) 6 Oct 22, 2022
Text to speech is a process to convert any text into voice. Text to speech project takes words on digital devices and convert them into audio. Here I have used Google-text-to-speech library popularly known as gTTS library to convert text file to .mp3 file. Hope you like my project!

Text to speech (using Python) Text to speech is a process to convert any text into voice. Text to speech project takes words on digital devices and co

null 19 Jun 30, 2022
์ดˆ์„ฑ ํ•ด์„๊ธฐ based on ko-BART

์ดˆ์„ฑ ํ•ด์„๊ธฐ ๊ฐœ์š” ํ•œ๊ตญ์–ด ์ดˆ์„ฑ๋งŒ์œผ๋กœ ์ด๋ฃจ์–ด์ง„ ๋ฌธ์žฅ์„ ์ž…๋ ฅํ•˜๋ฉด, ์™„์„ฑ๋œ ๋ฌธ์žฅ์„ ์˜ˆ์ธกํ•˜๋Š” ์ดˆ์„ฑ ํ•ด์„๊ธฐ์ž…๋‹ˆ๋‹ค. ์ดˆ์„ฑ: ใ„ดใ„ด ใ„ดใ„น ใ…ˆใ…‡ใ…Ž ์˜ˆ์ธก ๋ฌธ์žฅ: ๋‚˜๋Š” ๋„ˆ๋ฅผ ์ข‹์•„ํ•ด ๋ชจ๋ธ ๋ชจ๋ธ์€ SKT-AI์—์„œ ๊ณต๊ฐœํ•œ Ko-BART๋ฅผ ์ด์šฉํ•ฉ๋‹ˆ๋‹ค. ๋ฐ์ดํ„ฐ ๋ฌธ์žฅ ๋‹จ์œ„๋กœ ์ด๋ฃจ์–ด์ง„ ์•„๋ฌด ์ฝ”ํผ์Šค๋‚˜

Dawoon Jung 29 Oct 28, 2022
In this repository, I have developed an end to end Automatic speech recognition project. I have developed the neural network model for automatic speech recognition with PyTorch and used MLflow to manage the ML lifecycle, including experimentation, reproducibility, deployment, and a central model registry.

End to End Automatic Speech Recognition In this repository, I have developed an end to end Automatic speech recognition project. I have developed the

Victor Basu 22 Nov 13, 2022
Colibri core is an NLP tool as well as a C++ and Python library for working with basic linguistic constructions such as n-grams and skipgrams (i.e patterns with one or more gaps, either of fixed or dynamic size) in a quick and memory-efficient way. At the core is the tool ``colibri-patternmodeller`` whi ch allows you to build, view, manipulate and query pattern models.

Colibri Core by Maarten van Gompel, [email protected], Radboud University Nijmegen Licensed under GPLv3 (See http://www.gnu.org/licenses/gpl-3.0.html

Maarten van Gompel 122 Nov 17, 2022
Text-Summarization-using-NLP - Text Summarization using NLP to fetch BBC News Article and summarize its text and also it includes custom article Summarization

Text-Summarization-using-NLP Text Summarization using NLP to fetch BBC News Arti

Kumar Saksham 21 Aug 6, 2022
Continuously update some NLP practice based on different tasks.

NLP_practice We will continuously update some NLP practice based on different tasks. prerequisites Software pytorch >= 1.10 torchtext >= 0.11.0 sklear

null 0 Jan 5, 2022