llm-jp / llama-mimiLinks
Llama-Mimi is a speech language model that uses a unified tokenizer (Mimi) and a single Transformer decoder (Llama) to jointly model sequences of interleaved semantic and acoustic tokens.
☆28Updated 3 months ago
Alternatives and similar repositories for llama-mimi
Users that are interested in llama-mimi are comparing it to the libraries listed below
Sorting:
- LoRA-based phoneme/prosody control for LLM-based TTS with no G2P - Lightweight adapter for edit and control the target language's phoneme…☆22Updated 4 months ago
- Code associated with the paper: CTC-DRO: Robust Optimization for Reducing Language Disparities in Speech Recognition.☆15Updated 7 months ago
- SpeechGLUE is a speech version of the GLUE benchmark, driven by text-to-speech.☆13Updated 2 years ago
- My vocoder experiments☆31Updated 5 months ago
- A TTS Trained on Universal Audio.☆41Updated 7 months ago
- This app is intended to automatically create a corpus for ASR systems using pseudo-labeling.☆27Updated last year
- a Neural Vocoder supporting Ring Attention, Conformer and NSF.☆24Updated 5 months ago
- This is not remotely close to a finished product, and does not intend to nor does this claim to be working fine-tuning code for MaskGCT. …☆13Updated last year
- Audio tokenization, in the fastest way possible!☆53Updated last year
- LEMAS‑TTS is a multilingual zero‑shot text‑to‑speech system, supporting 10 languages: Chinese English Spanish Russian French German Ital…☆24Updated this week
- GPT for FACodec☆13Updated last year
- Text-to-Speech Latency Benchmark☆22Updated 6 months ago
- Zero-Shot Foreign Accent Conversion without a Native Reference☆36Updated last year
- The YouTube Text-To-Speech dataset is comprised of waveform audio extracted from YouTube videos alongside their English transcriptions☆52Updated 4 years ago
- Unofficial implementation of ConvNeXt-TTS powered by lightning☆17Updated last year
- PyTorch implementation of Miipher-2 [2025] which is a speech restoration model by Google DeepMind☆62Updated 3 months ago
- Collection of scripts from mHuBERT-147.☆32Updated last year
- Conformer block with Rotary Position Embedding, modified from lucidrains' implement☆16Updated last year
- ☆58Updated last year
- Generate audio datasets for training Text-To-Speech models, through smart audio splitting with silence detection, and transcription using…☆30Updated 2 years ago
- SpeechPlus: Small LLM-Based Text-to-Speech Library 🚀☆20Updated 7 months ago
- Temporary anonymous version☆22Updated last year
- ☆14Updated last year
- The official code for the SALMon🍣 benchmark (ICASSP 2025 - Oral)☆48Updated 4 months ago
- StyleTTS2 + Vocos as a Decoder☆13Updated 9 months ago
- This is a fork of the original fairseq repository (version 0.12.2) with added classes for training mHuBERT-147.☆20Updated last year
- Kanade is a speech tokenizer that encodes speech into compact content tokens and global embeddings and decodes them back to mel spectrogr…☆24Updated 2 months ago
- Open TTS models, built for streaming on the edge☆44Updated 9 months ago
- ☆15Updated 2 months ago
- My hybrid TTS network that combines, VALL-E, VoiceBox, SpeechFlow, Seamless and TortoiseTTS into one☆26Updated last year