mtkresearch / TASTE-SpokenLMLinks
A method that directly addresses the modality gap by aligning speech token with the corresponding text transcription during the tokenization stage.
☆106Updated 3 months ago
Alternatives and similar repositories for TASTE-SpokenLM
Users that are interested in TASTE-SpokenLM are comparing it to the libraries listed below
Sorting:
- Code for DeSTA2.5-Audio, general-purpose LALM☆128Updated 3 weeks ago
- Code and model for ICASSP 2025 Paper "Developing Instruction-Following Speech Language Model Without Speech Instruction-Tuning Data"☆119Updated 5 months ago
- Official implementation of MelHuBERT☆68Updated last year
- Official release of StyleTalk dataset.☆70Updated last year
- A low-bitrate single-codebook 16 / 24 kHz speech codec based on focal modulation☆135Updated last month
- A Benchmark for Evaluating Turn-Taking and Overlap Handling in Full-Duplex Spoken Dialogue Models☆112Updated 3 months ago
- Streamable Text-to-Speech model using a language modeling approach, without vector quantization☆106Updated 7 months ago
- [ACL 2024] Generative Pre-Trained Speech Language Model with Efficient Hierarchical Transformer☆67Updated last year
- A large-scale speech corpus introduced in Spark-TTS, built from diverse open-source datasets for training text-to-speech (TTS) systems.☆101Updated 7 months ago
- Official Code for SyllableLM: Learning Coarse Semantic Units for Speech Language Models☆58Updated 5 months ago
- WavReward: Spoken Dialogue Models With Generalist Reward Evaluators☆54Updated 7 months ago
- Codebase for 'Scaling Rich Style-Prompted Text-to-Speech Datasets'☆148Updated 9 months ago
- ☆70Updated last year
- Official implementation for Fast-HuBERT: An Efficient Training Framework for Self-Supervised Speech Representation Learning☆95Updated last year
- Implementation of Acoustic BPE (Shen et al., 2024), extended for RVQ-based Neural Audio Codecs☆75Updated 3 weeks ago
- [NeurIPS' 25] Benchmark for evaluating TTS models on complex prosodic, expressiveness, and linguistic challenges.☆181Updated 3 weeks ago
- Official code for Interspeech 2023 paper "Self-supervised Fine-tuning for Improved Content Representations by Speaker-invariant Clusterin…☆62Updated 2 years ago
- All generative model in one for better TTS model☆74Updated last year
- 《SpeechGen: Unlocking the Generative Power of Speech Language Models with Prompts》☆77Updated 2 years ago
- ☆61Updated last year
- Generative Expressive Conversational Speech Synthesis (Accepted by MM'2024)☆62Updated last year
- VoxInstruct: Expressive Human Instruction-to-Speech Generation with Unified Multilingual Codec Language Modelling☆93Updated last year
- The open source code for SimpleSpeech series☆143Updated last year
- A trainer for SNAC (Multi-Scale Neural Audio Codec) has replaced the decoder with Vocos.☆64Updated last year
- Official code for "F5R-TTS: Improving Flow-Matching based Text-to-Speech with Group Relative Policy Optimization"☆141Updated 6 months ago
- [EMNLP 2024] ESC: Efficient Speech Coding with Cross-Scale Residual Vector Quantized Transformers☆124Updated 9 months ago
- Unified Speech Language Model for paper "SpeechTokenizer: Unified Speech Tokenizer for Speech Large Language Models"(ICLR 2024)☆151Updated 2 years ago
- Evaluation Protocol for Large-Scale Zero-Shot TTS Literature☆89Updated 9 months ago
- The TTSDS benchmark evaluates synthetic speech quality by considering prosody, speaker identity, and intelligibility, comparing these fac…☆72Updated 3 months ago
- Official GitHub repository for paper "SAKURA: On the Multi-hop Reasoning of Large Audio-Language Models Based on Speech and Audio Informa…☆20Updated 4 months ago