ictnlp / NAST-S2x
A fast speech-to-speech & speech-to-text translation model that supports simultaneous decoding and offers 28× speedup.
☆60Updated 2 weeks ago
Related projects ⓘ
Alternatives and complementary repositories for NAST-S2x
- Code for ACL 2024 main conference paper "Can We Achieve High-quality Direct Speech-to-Speech Translation Without Parallel Speech Data?".☆23Updated 4 months ago
- AIR-Bench: Benchmarking Large Audio-Language Models via Generative Comprehension☆50Updated 2 months ago
- Code and pretrained models for "DUB: Discrete Unit Back-translation for Speech Translation" (ACL 2023 Findings)☆26Updated last year
- Official release of StyleTalk dataset.☆57Updated 4 months ago
- Unified Speech Language Model for paper "SpeechTokenizer: Unified Speech Tokenizer for Speech Large Language Models"(ICLR 2024)☆136Updated last year
- BLSP-Emo: Towards Empathetic Large Speech-Language Models☆36Updated 5 months ago
- SLMTokBench for paper "SpeechTokenizer: Unified Speech Tokenizer for Speech Large Language Models"☆33Updated last year
- [ACL 2024] Generative Pre-Trained Speech Language Model with Efficient Hierarchical Transformer☆33Updated last week
- [NeurIPS 2024] SD-Eval: A Benchmark Dataset for Spoken Dialogue Understanding Beyond Words☆42Updated 4 months ago
- Real-time Speech-Text Foundation Model Toolkit (wip)☆119Updated 3 weeks ago
- List of direct speech-to-speech translation papers.☆31Updated last year
- The open source code for LLM-Codec☆114Updated 2 months ago
- AudioBench: A Universal Benchmark for Audio Large Language Models☆89Updated last month
- ☆34Updated 6 months ago
- All generative model in one for better TTS model☆66Updated 2 months ago
- Code for NeurIPS 2023 paper "DASpeech: Directed Acyclic Transformer for Fast and High-quality Speech-to-Speech Translation".☆60Updated 3 months ago
- ☆26Updated last year
- The official repository of SpeechCraft dataset, a large-scale expressive bilingual speech dataset with natural language descriptions.☆49Updated last month
- Official repo for CoVoMix: Advancing Zero-Shot Speech Generation for Human-like Multi-talker Conversations☆28Updated last month
- [ICASSP 2024] KNN-CTC: Enhancing ASR via Retrieval of CTC Pseudo Labels☆28Updated 7 months ago
- 《SpeechGen: Unlocking the Generative Power of Speech Language Models with Prompts》☆74Updated last year
- Models and code for RepCodec: A Speech Representation Codec for Speech Tokenization☆157Updated 3 months ago
- ☆28Updated this week
- ☆21Updated last week
- ☆10Updated 7 months ago
- Official Code for ParrotTTS☆41Updated 3 weeks ago
- Generative Expressive Conversational Speech Synthesis (Accepted by MM'2024)☆40Updated last week
- Evaluation Protocol for Large-Scale Zero-Shot TTS Literature☆64Updated last month
- Generative Expressive Conversational Speech Synthesis (Accepted by MM'2024)☆38Updated last week
- [ICASSP 2024] StoryTTS: A Highly Expressive Text-to-Speech Dataset with Rich Textual Expressiveness Annotations☆135Updated 6 months ago