idiap / contextual-biasing-on-gpusLinks
Implementation of the contextual biasing for ASR decoding on GPUs without lattice generation. The code supports submission to Interspeech 2023.
☆21Updated 2 years ago
Alternatives and similar repositories for contextual-biasing-on-gpus
Users that are interested in contextual-biasing-on-gpus are comparing it to the libraries listed below
Sorting:
- Python wrappers for Kaldi Levenshtein's distance and alignment code.☆68Updated 6 months ago
- multilingual speech aligner☆77Updated 2 years ago
- ☆26Updated 2 months ago
- End-to-end MOdeling of ASR (Automatic Speech Recognition)☆33Updated 2 years ago
- streaming attention networks for end-to-end automatic speech recognition☆55Updated 5 years ago
- Some fast-ish algorithms for batch text search in moderate-sized collections, intended for data cleanup☆77Updated 5 months ago
- ☆37Updated 4 years ago
- Pronunciation-assisted Subword Modeling☆31Updated 6 years ago
- A fast parallel PyTorch implementation of the "CIF: Continuous Integrate-and-Fire for End-to-End Speech Recognition" https://arxiv.org/ab…☆34Updated last year
- wav2vec2 audio classification for prosodic boundary detection and other tasks☆42Updated 2 years ago
- Dynamic Chunk Streaming and Offline Conformer based on athena-team/Athena.☆44Updated 3 years ago
- ☆67Updated 3 years ago
- Data and code related to the ICASSP submission "A comparison of methods for OOV-word recognition"☆17Updated 4 years ago
- CMU multilingual speech repository☆30Updated 3 years ago
- Speech samples and code of BEdit-TTS☆34Updated 2 years ago
- A CSRankings-like index for speech researchers☆35Updated last year
- Code for InterSpeech 2024 Paper: LipGER: Visually-Conditioned Generative Error Correction for Robust Automatic Speech Recognition☆18Updated last year
- Segment a given audio into utterances using a trained end-to-end ASR model.☆74Updated 5 years ago
- ADAPTING SELF-SUPERVISED MODELS TO MULTI-TALKER SPEECH RECOGNITION USING SPEAKER EMBEDDINGS☆31Updated 2 years ago
- Python wrapper for kaldi's arpa2fst☆38Updated 3 months ago
- ☆44Updated 2 years ago
- ☆37Updated 3 years ago
- This is the source code of the paper "Neural grapheme-to-phoneme conversion with pretrained grapheme models☆47Updated 3 years ago
- Clustering-based methods for overlapping diarization☆81Updated last year
- Keyword spotting and forced alignment in any language☆79Updated 3 months ago
- Implementation of CoBERT: Self-Supervised Speech Representation Learning Through Code Representation Learning☆48Updated 2 years ago
- Memory efficient transducer loss computation☆69Updated 3 years ago
- LightHuBERT: Lightweight and Configurable Speech Representation Learning with Once-for-All Hidden-Unit BERT☆73Updated 3 years ago
- ☆37Updated 4 years ago
- Official implementation for Fast-HuBERT: An Efficient Training Framework for Self-Supervised Speech Representation Learning☆95Updated last year