Pinned Loading

1. ictnlp/LLaMA-Omni ictnlp/LLaMA-Omni Public

   LLaMA-Omni is a low-latency and high-quality end-to-end speech interaction model built upon Llama-3.1-8B-Instruct, aiming to achieve speech capabilities at the GPT-4o level.

   Python 2.6k 174

2. ictnlp/DASpeech ictnlp/DASpeech Public

   Code for NeurIPS 2023 paper "DASpeech: Directed Acyclic Transformer for Fast and High-quality Speech-to-Speech Translation".

   Python 60 5

3. ictnlp/STEMM ictnlp/STEMM Public

   Code for ACL 2022 main conference paper "STEMM: Self-learning with Speech-text Manifold Mixup for Speech Translation".

   Python 36 7

4. ictnlp/ComSpeech ictnlp/ComSpeech Public

   Code for ACL 2024 main conference paper "Can We Achieve High-quality Direct Speech-to-Speech Translation Without Parallel Speech Data?".

   Python 23 6

5. ictnlp/CRESS ictnlp/CRESS Public

   Code for ACL 2023 main conference paper "Understanding and Bridging the Modality Gap for Speech Translation".

   Python 16 2

6. ga642381/speech-trident ga642381/speech-trident Public

   Awesome speech/audio LLMs, representation learning, and codec models

   709 37