flashlight / text
Text utilities, including beam search decoding, tokenizing, and more, built for use in Flashlight.
☆66Updated 3 weeks ago
Alternatives and similar repositories for text:
Users that are interested in text are comparing it to the libraries listed below
- This repository contains data used in the NAACL 2021 Paper - Proteno: Text Normalization with Limited Data for Fast Deployment in Text to…☆42Updated 3 years ago
- ☆56Updated 2 years ago
- ☆34Updated 4 months ago
- Sequence algorithms for use in Flashlight.☆13Updated 8 months ago
- Standalone implementation of the CUDA-accelerated WFST Decoder available in Riva☆83Updated last month
- asr2k☆48Updated 7 months ago
- Some fast-ish algorithms for batch text search in moderate-sized collections, intended for data cleanup☆62Updated 4 months ago
- A toolkit for Spoken Language Understanding Evaluation (SLUE) benchmark. Refer paper https://arxiv.org/abs/2111.10367 for more details. O…☆63Updated 10 months ago
- Python wrapper for kaldi's arpa2fst☆38Updated last month
- A collection of utilities for handling IPA phones.☆25Updated last year
- Python wrappers for Kaldi Levenshtein's distance and alignment code.☆62Updated 10 months ago
- Pronunciation-assisted Subword Modeling☆29Updated 5 years ago
- A torch implementation of a recursion which turns out to be useful for RNN-T.☆140Updated last year
- An easy way to fine-tune Wav2Vec 2.0 for low-resource languages.☆81Updated last year
- Example code for a neural transducer model.☆61Updated 11 months ago
- Various speech datasets made available to the public☆107Updated last month
- CMU multilingual speech repository☆31Updated 2 years ago
- Kaldi style neural network training in pytorch for use in place of nnet3 in Kaldi.☆26Updated 5 months ago
- Small compression utility☆35Updated 6 months ago
- Torch-based tool for quantizing high-dimensional vectors using additive codebooks☆51Updated 2 years ago
- Memory efficient transducer loss computation☆68Updated 2 years ago
- ☆20Updated 6 years ago
- ☆67Updated 2 years ago
- Incorporating KenLM language model with HuggingFace implementation of Wav2Vec2CTC Model using beam search decoding☆72Updated 3 years ago
- ☆74Updated 3 years ago
- An online speech recognition extension toolkit of Kaldi☆56Updated 3 years ago
- Segment a given audio into utterances using a trained end-to-end ASR model.☆72Updated 4 years ago
- Repo for the FB AI Speech team.☆22Updated 3 years ago
- WarpRNNT loss ported in Numba CPU/CUDA for Pytorch☆16Updated 2 years ago