ictnlp / ComSpeechLinks
Code for ACL 2024 main conference paper "Can We Achieve High-quality Direct Speech-to-Speech Translation Without Parallel Speech Data?".
☆24Updated 11 months ago
Alternatives and similar repositories for ComSpeech
Users that are interested in ComSpeech are comparing it to the libraries listed below
Sorting:
- A fast speech-to-speech & speech-to-text translation model that supports simultaneous decoding and offers 28× speedup.☆69Updated 8 months ago
- Streamable Text-to-Speech model using a language modeling approach, without vector quantization☆92Updated last month
- Official release of StyleTalk dataset.☆66Updated 11 months ago
- ☆35Updated last year
- [ACL 2024] Generative Pre-Trained Speech Language Model with Efficient Hierarchical Transformer☆58Updated 7 months ago
- ☆18Updated last year
- ☆13Updated last year
- ☆28Updated 4 months ago
- Generative Expressive Conversational Speech Synthesis (Accepted by MM'2024)☆73Updated 7 months ago
- ☆74Updated 2 weeks ago
- Benchmark for evaluating TTS models on complex prosodic, expressiveness, and linguistic challenges.☆45Updated 2 weeks ago
- ☆33Updated 2 months ago
- LLaST: Improved End-to-end Speech Translation System Leveraged by Large Language Models☆25Updated 10 months ago
- ☆40Updated 4 months ago
- ☆25Updated 2 years ago
- Official Code for ParrotTTS☆51Updated 8 months ago
- Inference code for Audiodec-Valle-Wenetspeech4TTS☆50Updated 11 months ago
- ☆50Updated 2 months ago
- [ACMMM'2024] Generative Expressive Conversational Speech Synthesis☆35Updated 7 months ago
- Streaming Vocos☆27Updated 2 weeks ago
- SLMTokBench for paper "SpeechTokenizer: Unified Speech Tokenizer for Speech Large Language Models"☆35Updated last year
- Generative Expressive Conversational Speech Synthesis (Accepted by MM'2024)☆59Updated 7 months ago
- Speaker-aware CTC (SACTC) for multi-talker overlapped speech recognition.☆20Updated 3 weeks ago
- 《SpeechGen: Unlocking the Generative Power of Speech Language Models with Prompts》☆73Updated 2 years ago
- Code and pretrained models for "DUB: Discrete Unit Back-translation for Speech Translation" (ACL 2023 Findings)☆28Updated last year
- [Findings of NAACL 2024] Source code of paper CM-TTS: Enhancing Real Time Text-to-Speech Synthesis Efficiency through Weighted Samplers a…☆65Updated last year
- Text-To-Speech for NotebookLM☆32Updated 6 months ago
- ☆25Updated 10 months ago
- E2E TTS using Conditional Flow Matching (Experimental*)☆69Updated last year
- (WIP)long form speech generatoins☆31Updated 2 months ago