A Implementation of SpecAugment with Tensorflow & Pytorch, introduced by Google Brain
-
Updated
Apr 5, 2022 - Python
#
specaugment
Here are 17 public repositories matching this topic...
SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition
-
Updated
Sep 5, 2020 - Python
Tensor2tensor experiment with SpecAugment
-
Updated
May 13, 2019 - Python
End-to-end speech recognition on AISHELL dataset.
-
Updated
Nov 9, 2021 - Python
fast SpecAugmentation code with numpy and scipy
-
Updated
Jul 5, 2019 - Python
tf 2.0 implementation of Listen, attend and spell
recognition tensorflow keras speech listen speech-recognition spell 2 tf listen-attend-and-spell attend tensorflow2 specaugment
-
Updated
Jan 19, 2021 - Python
A minimalistic Tensorflow 2.x Keras layer which applies SpecAugment to its input
-
Updated
Aug 11, 2021 - Jupyter Notebook
Emotion recognition with IEMOCAP datasets. We compare the results with SpecAugmentation and CodecAugmentation. For audio codec implementation, we have selected opus.
-
Updated
Apr 21, 2021 - Jupyter Notebook
Radio signal spectrogram classification with PyTorch, SpecAugment-based data augmentation, and a pretrained EfficientNet-B0 model for four-class signal recognition.
computer-vision deep-learning signal-processing cnn pytorch image-classification spectrogram transfer-learning specaugment efficientnet radio-signals efficientnet-b0 timm
-
Updated
May 8, 2026 - Jupyter Notebook
XSpeech: A Novel Deep Learning Approach to Classifying Stutters
-
Updated
Aug 3, 2025 - Jupyter Notebook
PyTorch implementation of Transformer-based Automatic Speech Recognition with attention mechanisms, SpecAugment, CTC loss, and mixed precision training. Achieves competitive WER/CER on LibriSpeech.
machine-learning natural-language-processing deep-learning pytorch transformer speech-recognition speech-to-text attention-mechanism audio-processing ctc encoder-decoder librispeech asr-model specaugment wandb
-
Updated
Feb 21, 2025 - Python
Speech recognition toolkit featuring SpecAugment, Whisper fine-tuning, LAS ASR, synthetic data generation, benchmarking, and a desktop GUI. Built with PyTorch, Transformers, Librosa, and CustomTkinter.
machine-learning gui deep-learning transformers pytorch tts speech-recognition librosa whisper asr specaugment customtkinter
-
Updated
Jul 1, 2026 - Python
REST API based on PyTorch (ResNet18) for classifying 50 categories of natural and household sounds (rain, chainsaw, glass breaking, etc.) from audio files. Mel spectrograms + FastAPI. Val accuracy 86%. Trained in Google Colab on ESC-50.
python machine-learning computer-vision deep-learning rest-api cnn pytorch transfer-learning audio-classification audio-processing restnet sound-classification torchaudio google-colab uvicorn mel-spectrogram esc-50 fastapi specaugment restnet18
-
Updated
Aug 13, 2026 - Jupyter Notebook
Performs data augmentation as according to the SpecAugment paper. Modified from Lingvo (TensorFlow > 1.10.0).
-
Updated
Jan 26, 2022 - Python
Simple numpy-based implementation of SpecAugment
-
Updated
Sep 25, 2023 - Python
FastAPI service for music genre classification (GTZAN, 10 classes) using a CNN with Mel spectrograms. 78% test accuracy, SpecAugment data augmentation, fully offline inference.
python machine-learning deep-learning rest-api cnn pytorch music-genre-classification audio-classification torchaudio mel-spectrogram fastapi gtzan specaugment
-
Updated
Aug 13, 2026 - Jupyter Notebook
An Audio Classification task with two types of inputs to the CNN models for intended work using Tensorflow.
docker spectrogram audio-classification cnn-keras waveform-data specaugment streamlit-webapp very-deep-cnns
-
Updated
Jul 15, 2025 - Jupyter Notebook
Improve this page
Add a description, image, and links to the specaugment topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the specaugment topic, visit your repo's landing page and select "manage topics."