mtkresearch / TASTE-SpokenLMLinks
A method that directly addresses the modality gap by aligning speech token with the corresponding text transcription during the tokenization stage.
☆89Updated 2 weeks 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☆113Updated last month
- Code and model for ICASSP 2025 Paper "Developing Instruction-Following Speech Language Model Without Speech Instruction-Tuning Data"☆113Updated 2 months ago
- Official implementation of MelHuBERT☆67Updated 10 months ago
- Official release of StyleTalk dataset.☆69Updated last year
- Official code for Interspeech 2023 paper "Self-supervised Fine-tuning for Improved Content Representations by Speaker-invariant Clusterin…☆57Updated 2 years ago
- Official Code for SyllableLM: Learning Coarse Semantic Units for Speech Language Models☆58Updated 2 months ago
- Streamable Text-to-Speech model using a language modeling approach, without vector quantization☆98Updated 4 months ago
- A Benchmark for Evaluating Turn-Taking and Overlap Handling in Full-Duplex Spoken Dialogue Models☆74Updated 3 weeks ago
- 《SpeechGen: Unlocking the Generative Power of Speech Language Models with Prompts》☆75Updated 2 years ago
- [ACL 2024] Generative Pre-Trained Speech Language Model with Efficient Hierarchical Transformer☆61Updated 10 months ago
- A low-bitrate single-codebook 16 kHz speech codec based on focal modulation☆95Updated this week
- WavReward: Spoken Dialogue Models With Generalist Reward Evaluators☆53Updated 4 months ago
- A trainer for SNAC (Multi-Scale Neural Audio Codec) has replaced the decoder with Vocos.☆58Updated 10 months ago
- Collection of works for evaluating (and analyzing) large audio-language models (LALMs)☆35Updated last month
- The open source code for LLM-Codec☆138Updated last year
- Codebase for 'Scaling Rich Style-Prompted Text-to-Speech Datasets'☆135Updated 5 months ago
- Implementation of Acoustic BPE (Shen et al., 2024), extended for RVQ-based Neural Audio Codecs☆69Updated 2 months ago
- LibriSpeech-Long is a benchmark dataset for long-form speech generation and processing. Released as part of "Long-Form Speech Generation …☆84Updated 8 months ago
- ☆70Updated last year
- Unified Speech Language Model for paper "SpeechTokenizer: Unified Speech Tokenizer for Speech Large Language Models"(ICLR 2024)☆149Updated 2 years ago
- Implementation of SoundStorm built upon SpeechTokenizer.☆114Updated last year
- A single-layer, streaming codec model providing SOTA audio quality and discrete tokens designed for superior downstream modelability.☆98Updated 3 months ago
- This is the code for paper: XY-Tokenizer: Mitigating the Semantic-Acoustic Conflict in Low-Bitrate Speech Codecs. Demos, technical insigh…☆70Updated 2 months ago
- Extract phoneme-level timestamps from speeh audio.☆72Updated last week
- ☆41Updated 7 months ago
- All generative model in one for better TTS model☆73Updated last year
- The open source code of ALMTokenizer2: Towards Low bit-rate and Semantic-rich Audio Tokenizer with Flow-based Scalar Diffusion Transforme…☆42Updated 2 weeks ago
- A large-scale speech corpus introduced in Spark-TTS, built from diverse open-source datasets for training text-to-speech (TTS) systems.☆87Updated 4 months ago
- Official code for "F5R-TTS: Improving Flow-Matching based Text-to-Speech with Group Relative Policy Optimization"☆117Updated 3 months ago
- Evaluation Protocol for Large-Scale Zero-Shot TTS Literature☆83Updated 6 months ago