erogol / BlaGPT
Experimental playground for benchmarking language model (LM) architectures, layers, and tricks on smaller datasets. Designed for flexible experimentation and exploration.
☆16Updated 2 weeks ago
Alternatives and similar repositories for BlaGPT:
Users that are interested in BlaGPT are comparing it to the libraries listed below
- Collection of scripts from mHuBERT-147.☆24Updated 3 months ago
- Implementation of Google's USM speech model in Pytorch☆30Updated last month
- ☆35Updated 10 months ago
- Official Code for ParrotTTS☆48Updated 4 months ago
- ☆18Updated 10 months ago
- Text-To-Speech for NotebookLM☆29Updated 2 months ago
- An official implementation of Style-Talker for Spoken Dialogue Generation☆17Updated last month
- GPT-style network for phonemization with durations of text☆63Updated 11 months ago
- [InterSpeech'2024] FluentEditor:Text-based Speech Editing by Considering Acoustic and Prosody Consistency☆51Updated 4 months ago
- Official repository of the IEEE SLT 2024 paper "Self-Supervised Syllable Discovery Based on Speaker-Disentangled HuBERT"☆34Updated 3 weeks ago
- Official Demo Page for DiTTo-TTS: Efficient and Scalable Zero-Shot Text-to-Speech with Diffusion Transformer☆32Updated 3 weeks ago
- ☆24Updated last year
- Just another FastSpeech 2 but cleaner code :)☆26Updated 8 months ago
- Pushing the Limits of Zero-shot End-to-End Speech Translation☆25Updated 2 months ago
- Interface Design for Self-Supervised Speech Models, Accepted to Interspeech2024☆15Updated 3 months ago
- ☆26Updated last year
- ☆36Updated 5 months ago
- SoloAudio: Target Sound Extraction with Language-oriented Audio Diffusion Transformer.☆78Updated 2 months ago
- This is a fork of the original fairseq repository (version 0.12.2) with added classes for training mHuBERT-147.☆15Updated 3 months ago
- A spoken version of the textual story cloze benchmark☆14Updated last year
- LLaST: Improved End-to-end Speech Translation System Leveraged by Large Language Models☆25Updated 6 months ago
- Contains the code associated with the ICLR submission for our text-to-speech diffusion model☆53Updated last year
- We introduce the LLAMA1 Test Set, a comprehensive open-domain world knowledge QA dataset for evaluating question-answering systems. We pr…☆17Updated 11 months ago
- Legible, Scalable, Reproducible Foundation Models with Named Tensors and Jax☆12Updated 8 months ago
- GPT for FACodec☆13Updated 11 months ago
- ☆43Updated 6 months ago
- Codebase and project page for EDMSound☆34Updated last year