PyTorch implementation of RNN-Transducer
RNN-Transducer are a form of sequence-to-sequence models that do not employ attention mechanisms. Unlike most sequence-to-sequence models, which typically need to process the entire input sequence (the waveform in our case) to produce an output (the sentence), the RNN-T continuously processes input samples and streams output symbols, a property that is welcome for speech dictation.
This repository contains only model code, but you can train with conformer with this repository.
This project recommends Python 3.7 or higher. We recommend creating a new virtual environment for this project (using virtual env or conda).
- Numpy:
pip install numpy(Refer here for problem installing Numpy). - Pytorch: Refer to PyTorch website to install the version w.r.t. your environment.
- warprnnt_pytorch: Refer to warp-transducer to install warprnnt_pytorch.
import torch
import torch.nn as nn
from rnnt import RNNTransducer
batch_size, sequence_length, dim = 3, 12345, 80
cuda = torch.cuda.is_available()
device = torch.device('cuda' if cuda else 'cpu')
inputs = torch.rand(batch_size, sequence_length, dim).to(device)
input_lengths = torch.IntTensor([12345, 12300, 12000])
targets = torch.LongTensor([[1, 3, 3, 3, 3, 3, 4, 5, 6, 2],
[1, 3, 3, 3, 3, 3, 4, 5, 2, 0],
[1, 3, 3, 3, 3, 3, 4, 2, 0, 0]]).to(device)
target_lengths = torch.LongTensor([9, 8, 7])
model = nn.DataParallel(RNNTransducer(num_classes=10)).to(device)
# Forward propagate
outputs = model(inputs, input_lengths, targets, target_lengths)
# Recognize input speech
outputs = model.module.recognize(inputs, input_lengths)If you have any questions, bug reports, and feature requests, please open an issue on github or
contacts sh951011@gmail.com please.
I appreciate any kind of feedback or contribution. Feel free to proceed with small issues like bug fixes, documentation improvement. For major contributions and new features, please discuss with the collaborators in corresponding issues.
I follow PEP-8 for code style. Especially the style of docstrings is important to generate documentation.
- Soohwan Kim @sooftware
- Contacts: sh951011@gmail.com