an open-source implementation of sequence-to-sequence based speech processing engine
Rust re-implementation of OpenFST - library for constructing, combining, optimizing, and searching weighted finite-state transducers (FSTs). A Python binding is also available.
Source code of the TinyOWS project. Please submit pull requests to the 'main' branch.
High-performance speech-to-text (ASR) inference and serving engine for NVIDIA GPUs: Whisper, Conformer, Zipformer, RNN-T, Paraformer, Qwen2-Audio. OpenAI-compatible API, streaming, CUDA kernels.
Play with Weighted Finite State Transducers (WFST) in the Julia language.
A Julia recipe for training an ASR system using the TIDIGITS database
Post processing for speech recognition
Weighted finite-state transducers in Rust, file-compatible with OpenFst, and a speech decoder built on them
基于 WFST 与 GNN 的物联网侧信道攻击框架，研究 IFTTT/TAP 智能家居自动化规则的隐私泄露风险 | IoT WFST side-channel attack framework for evaluating smart-home rule privacy leakage on Trigger-Action Platforms
Some very old scripts (about 4 years ago) written by myself to convert ARPA language model, HTK lattice, etc to weighted finite state transducers.
To associate your repository with the wfst topic, visit your repo's landing page and select "manage topics."