Rishit-dagli / Conformer
An implementation of Conformer: Convolution-augmented Transformer for Speech Recognition, a Transformer Variant in TensorFlow/Keras
☆42Updated 2 years ago
Related projects ⓘ
Alternatives and complementary repositories for Conformer
- SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition☆70Updated 4 years ago
- WavEncoder is a Python library for encoding audio signals, transforms for audio augmentation, and training audio classification models wi…☆89Updated 3 years ago
- A Mixed Sample Data Augmentation method for Training with Time-Frequency Domain Features☆10Updated 2 years ago
- A mini, simple, and fast end-to-end automatic speech recognition toolkit.☆47Updated last year
- ☆25Updated 2 years ago
- ☆79Updated last year
- ☆62Updated 2 months ago
- GSoC'2021 | TensorFlow implementation of Wav2Vec2☆89Updated 2 years ago
- Companion repository for the paper "A Comparison of Metric Learning Loss Functions for End-to-End Speaker Verification" published at SLSP…☆59Updated 4 years ago
- Speech Separation☆52Updated 8 months ago
- Code for the TASLP paper "PSLA: Improving Audio Tagging With Pretraining, Sampling, Labeling, and Aggregation".☆140Updated last year
- Conformer encoder + Transformer decoder with Hybrid CTC/attention☆12Updated 3 years ago
- PyTorch implementation of the LEAF audio frontend☆68Updated last year
- ☆105Updated 3 years ago
- Code repo for "Multi-Task Learning for Interpretable Weakly Labelled Sound Event Detection"☆16Updated 2 years ago
- Transformer implementation speciaized in speech recognition tasks using Pytorch.☆64Updated 2 years ago
- Spectra extraction tutorials based on torch and torchaudio.☆40Updated last year
- PyTorch implementation of "Squeezeformer: An Efficient Transformer for Automatic Speech Recognition" (NeurIPS 2022)☆130Updated 2 years ago
- The Additive Margin SincNet (AM-SincNet) is a new approach for speaker recognition problems which is based in the neural network architec…☆43Updated last year
- Clustering-based methods for overlapping diarization☆70Updated 10 months ago
- Speaker verification using ResnetSE (EER=0.0093) and ECAPA-TDNN☆89Updated 3 years ago
- pytorch implementation for MultiSpeech: Multi-Speaker Text to Speech with Transformer paper☆19Updated 2 years ago
- An implementation of Speech Emotion Recognition, based on HuBERT model, training with PyTorch and HuggingFace framework, and fine-tuning …☆32Updated 2 years ago
- ☆49Updated 4 months ago
- ☆53Updated 4 years ago
- The implementation of "A Recursive Network with Dynamic Attention for Monaural Speech Enhancement"☆77Updated last year
- Feature extractor for DL speech processing.☆65Updated 2 years ago
- ☆53Updated 5 months ago
- Library of TensorFlow layers for audio data processing and data augmentation☆20Updated 2 years ago