flashlight / textLinks
Text utilities, including beam search decoding, tokenizing, and more, built for use in Flashlight.
☆74Updated last month
Alternatives and similar repositories for text
Users that are interested in text are comparing it to the libraries listed below
Sorting:
- Standalone implementation of the CUDA-accelerated WFST Decoder available in Riva☆92Updated 8 months ago
- ☆37Updated 6 months ago
- ☆56Updated 2 years ago
- This repository contains data used in the NAACL 2021 Paper - Proteno: Text Normalization with Limited Data for Fast Deployment in Text to…☆45Updated 4 years ago
- Some fast-ish algorithms for batch text search in moderate-sized collections, intended for data cleanup☆77Updated 4 months ago
- asr2k☆52Updated last year
- Example code for a neural transducer model.☆66Updated last year
- Python wrapper for kaldi's arpa2fst☆38Updated 2 months ago
- Small compression utility☆37Updated 6 months ago
- Python wrappers for Kaldi Levenshtein's distance and alignment code.☆68Updated 5 months ago
- A toolkit for Spoken Language Understanding Evaluation (SLUE) benchmark. Refer paper https://arxiv.org/abs/2111.10367 for more details. O…☆65Updated last year
- A torch implementation of a recursion which turns out to be useful for RNN-T.☆145Updated 2 years ago
- Segment a given audio into utterances using a trained end-to-end ASR model.☆74Updated 5 years ago
- Incorporating KenLM language model with HuggingFace implementation of Wav2Vec2CTC Model using beam search decoding☆76Updated 4 years ago
- Torch-based tool for quantizing high-dimensional vectors using additive codebooks☆54Updated 3 years ago
- Multistream CNN for Robust Acoustic Modeling☆40Updated 4 years ago
- WarpRNNT loss ported in Numba CPU/CUDA for Pytorch☆17Updated 3 years ago
- Sequence algorithms for use in Flashlight.☆14Updated 7 months ago
- A fast parallel implementation of RNN Transducer.☆12Updated 6 months ago
- Various speech datasets made available to the public☆131Updated 10 months ago
- ☆67Updated 3 years ago
- A lightweight library to compute Diarization Error Rate (DER).☆62Updated 2 years ago
- Explore different way to mix speech model(wav2vec2, hubert) and nlp model(BART,T5,GPT) together☆47Updated 3 months ago
- ☆39Updated 3 years ago
- This repository describes our reproducible framework for assessing self-supervised representation learning from speech☆51Updated 4 years ago
- An easy way to fine-tune Wav2Vec 2.0 for low-resource languages.☆81Updated 2 years ago
- Official code for Wav2Seq☆96Updated 3 years ago
- The People’s Speech Dataset☆108Updated last year
- Memory efficient transducer loss computation☆69Updated 3 years ago
- Pronunciation-assisted Subword Modeling☆31Updated 6 years ago