This is the code for paper: XY-Tokenizer: Mitigating the Semantic-Acoustic Conflict in Low-Bitrate Speech Codecs
StreamUni is a framework that efficiently enables unified Large Speech-Language Models to accomplish streaming speech translation in a cohesive manner.
A single-stream speech language model based on WavLM
Reproducible speech language model evaluation with audio-text datasets, replay and HTTP adapters, lexical metrics, streaming timelines and local reports.
Build end-to-end speech models with unified audio-text training, causal decoding, and streaming protocols.
To associate your repository with the speech-language-models topic, visit your repo's landing page and select "manage topics."