salesforce / speech-datasets
Simplified recipes for preparing commonly used speech datasets, and a PyTorch-compatible Python data loader that can perform standard feature computations & data augmentations.
☆14Updated last year
Related projects: ⓘ
- Generate audio datasets for training Text-To-Speech models, through smart audio splitting with silence detection, and transcription using…☆27Updated last year
- Audio samples accompanying publications related to DF-Conformer, a speech enhancement model.☆20Updated last year
- Fast and differentiable hidden Markov model in C++☆15Updated last year
- A JAX library for building lattice-based speech transducer models☆39Updated 5 months ago
- Code for the paper: How Much Context Does My Attention-Based ASR System Need?☆9Updated 2 months ago
- A home for audio ML in JAX. Has common features, learnable frontends, pretrained supervised and self-supervised models.☆62Updated 2 years ago
- Source code for INTERSPEECH2020☆11Updated 4 years ago
- Speech in Flax/JAX☆15Updated 2 years ago
- This app is intended to automatically create a corpus for ASR systems using pseudo-labeling.☆27Updated 7 months ago
- ☆23Updated last year
- ☆22Updated 3 years ago
- Viterbi decoding in PyTorch☆23Updated 3 weeks ago
- A library of speech gadgets.☆13Updated last year
- Semi-supervised Learning for Multi-speaker Text-to-speech Synthesis Using Discrete Speech Representation☆38Updated 4 years ago
- Proposed splits for the LREC Wikipron paper☆13Updated 4 years ago
- Implementation of Google's USM speech model in Pytorch☆23Updated last week
- Prosodic Speech Segmentation with Transformers☆22Updated 6 months ago
- ☆42Updated 2 years ago
- Torch implementation of Whisper-guided DDPM based Voice Conversion☆49Updated last year
- SpeechGLUE is a speech version of the GLUE benchmark, driven by text-to-speech.☆13Updated last year
- GPT for FACodec☆13Updated 5 months ago
- ☆19Updated 5 years ago
- NU-Wave 2: A General Neural Audio Upsampling Model for Various Sampling Rates [WIP]☆24Updated 2 years ago
- This repo contains the baseline model recipes and pre-trained model for GramVanni hindi ASR challenge☆14Updated 2 years ago
- Based on https://github.com/fatchord/WaveRNN☆24Updated 4 years ago
- ☆15Updated last year
- ☆56Updated last year
- Implementation of "FastSpeech: Fast, Robust and Controllable Text to Speech"☆51Updated 4 years ago
- Temporary anonymous version☆22Updated 6 months ago
- Zero-Shot Foreign Accent Conversion without a Native Reference☆27Updated 4 months ago