sooftware/conformer has 1,137 GitHub stars and 191 forks. GitHot measured 0 stars in 24 hours, 0 in 7 days, and 0 in 15 days. Last checked 2026-11-22 00:30 UTC. Last push 2026-11-15.
計測したスター増加
- 24時間
- 0
- 7日間
- 0
- 15日間
- 0
- 1か月
- 履歴を収集中
期間ごとの純増数です。期間は重複しており、日別の値ではありません。未計測の値は空欄です。スター数は注目度の指標であり、品質の保証ではありません。
概要
[Unofficial] PyTorch implementation of "Conformer: Convolution-augmented Transformer for Speech Recognition" (INTERSPEECH 2020)
機械学習README.md
オリジナル
PyTorch implementation of Conformer: Convolution-augmented Transformer for Speech Recognition.
Transformer models are good at capturing content-based global interactions, while CNNs exploit local features effectively. Conformer combine convolution neural networks and transformers to model both local and global dependencies of an audio sequence in a parameter-efficient way. Conformer significantly outperforms the previous Transformer and CNN based models achieving state-of-the-art accuracies.

This repository contains only model code, but you can train with conformer at openspeech
Installation
This project recommends Python 3.7 or higher. We recommend creating a new virtual environment for this project (using virtual env or conda).
Prerequisites
- Numpy:
pip install numpy(Refer here for problem installing Numpy). - Pytorch: Refer to PyTorch website to install the version w.r.t. your environment.
Install from source
Currently we only support installation from source code using setuptools. Checkout the source code and run the following commands:
pip install -e .
Usage
import torch
import torch.nn as nn
from conformer import Conformer
batch_size, sequence_length, dim = 3, 12345, 80
cuda = torch.cuda.is_available()
device = torch.device('cuda' if cuda else 'cpu')
criterion = nn.CTCLoss().to(device)
inputs = torch.rand(batch_size, sequence_length, dim).to(device)
input_lengths = torch.LongTensor([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 = Conformer(num_classes=10,
input_dim=dim,
encoder_dim=32,
num_encoder_layers=3).to(device)
# Forward propagate
outputs, output_lengths = model(inputs, input_lengths)
# Calculate CTC Loss
loss = criterion(outputs.transpose(0, 1), targets, output_lengths, target_lengths)
Troubleshoots and Contributing
If you have any questions, bug reports, and feature requests, please open an issue on github or
contacts [email protected] 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.
Code Style
I follow PEP-8 for code style. Especially the style of docstrings is important to generate documentation.
Reference
- Conformer: Convolution-augmented Transformer for Speech Recognition
- Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context
- kimiyoung/transformer-xl
- espnet/espnet
Author
- Soohwan Kim @sooftware
- Contacts: [email protected]
関連プロジェクトを探す
読み込み中…