google-research / lastLinks
A JAX library for building lattice-based speech transducer models
☆45Updated 7 months ago
Alternatives and similar repositories for last
Users that are interested in last are comparing it to the libraries listed below
Sorting:
- ☆56Updated 2 years ago
- Applications using the GTN library and code to reproduce experiments in "Differentiable Weighted Finite-State Transducers"☆84Updated 2 years ago
- The accompanying code for "Exploring the limits of decoder-only models trained on public speech recognition corpora" (Ankit Gupta, George…☆19Updated 9 months ago
- Standalone implementation of the CUDA-accelerated WFST Decoder available in Riva☆91Updated 4 months ago
- ☆12Updated 4 years ago
- asr2k☆51Updated last year
- Official repository for NAST: Noise Aware Speech Tokenization for Speech Language Models (Interspeech 2024) https://arxiv.org/abs/2406.11…☆46Updated last year
- Code for the paper: How Much Context Does My Attention-Based ASR System Need?☆10Updated 2 months ago
- BurrMill core☆21Updated 3 years ago
- Prosodic Speech Segmentation with Transformers☆25Updated last year
- Multistream CNN for Robust Acoustic Modeling☆40Updated 4 years ago
- ☆27Updated last month
- Speech-MASSIVE is a multilingual Spoken Language Understanding (SLU) dataset comprising the speech counterpart for a portion of the MASSI…☆22Updated 10 months ago
- A collection of utilities for handling IPA phones.☆25Updated last year
- ☆37Updated 2 months ago
- ☆13Updated 3 years ago
- ☆20Updated 6 years ago
- A Python-based modular toolbox for building Deep Neural Network models (using PyTorch) for statistical parametric speech synthesis☆23Updated 3 years ago
- Audio samples accompanying publications related to DF-Conformer, a speech enhancement model.☆30Updated last month
- Modular and extensible speech recognition library leveraging pytorch-lightning and hydra.☆46Updated 4 years ago
- Transcribing Speech with Multinomial Diffusion, training code and models.☆77Updated last year
- CMU multilingual speech repository☆31Updated 3 years ago
- The official code for the SALMon🍣 benchmark (ICASSP 2025 - Oral)☆46Updated 3 months ago
- Torch-based tool for quantizing high-dimensional vectors using additive codebooks☆54Updated 3 years ago
- WarpRNNT loss ported in Numba CPU/CUDA for Pytorch☆17Updated 3 years ago
- This app is intended to automatically create a corpus for ASR systems using pseudo-labeling.☆27Updated last year
- A new metric for evaluating end-to-end speech recognition and disfluency removal systems☆19Updated 4 years ago
- Implementation of Google's USM speech model in Pytorch☆31Updated 3 months ago
- Torch implementation of Whisper-guided DDPM based Voice Conversion☆49Updated 2 years ago
- Data and code related to the ICASSP submission "A comparison of methods for OOV-word recognition"☆17Updated 3 years ago