VikhrModels / Salt
☆39Updated this week
Alternatives and similar repositories for Salt:
Users that are interested in Salt are comparing it to the libraries listed below
- ☆31Updated 6 months ago
- Простой IPA фонемизатор на базе ruaccent-encoder☆18Updated 5 months ago
- T5-based (russian) text normalization☆20Updated last year
- Framework for processing and filtering datasets☆27Updated 8 months ago
- ☆45Updated 3 weeks ago
- Use quantized versions of Whisper to speed up inference☆12Updated 5 months ago
- Simple audio AE☆12Updated 4 months ago
- Effective LLM Alignment Toolkit☆125Updated 3 weeks ago
- Modified Arena-Hard-Auto LLM evaluation toolkit with an emphasis on Russian language☆39Updated 2 weeks ago
- Open TTS models, built for streaming on the edge☆39Updated 2 weeks ago
- ☆22Updated last year
- ☆26Updated this week
- Простой нормализатор текстов перед синтезом речи☆25Updated 10 months ago
- Normalize Text in Russian☆26Updated last year
- RuBLiMP: Russian Benchmark of Linguistic Minimal Pairs☆17Updated last month
- Top ML papers of the week.☆30Updated this week
- MERA (Multimodal Evaluation for Russian-language Architectures) is a new open benchmark for the Russian language for evaluating fundament…☆62Updated 5 months ago
- Generative Modeling with Bayesian Sample Inference☆19Updated last week
- ☆104Updated this week
- Provide Gradio custom components to make the diarization-based audio labeling process easier and faster.☆61Updated 3 weeks ago
- Official repository for the paper "NeuZip: Memory-Efficient Training and Inference with Dynamic Compression of Neural Networks". This rep…☆56Updated 5 months ago
- ☆18Updated 3 months ago
- Joint speech-language model - respond directly to audio!☆30Updated 10 months ago
- MERA (Multimodal Evaluation for Russian-language Architectures) is a new open benchmark for the Russian language for evaluating SOTA mode…☆21Updated this week
- Official repository of Wavehax vocoder☆46Updated 4 months ago
- Russian open TTS dataset☆12Updated 5 years ago
- A benchmark for role-playing language models☆90Updated 2 weeks ago
- BUD-E (Buddy) is an open-source voice assistant framework that facilitates seamless interaction with AI models and APIs, enabling the cre…☆18Updated 5 months ago
- Official implementation of the paper "Linear Transformers with Learnable Kernel Functions are Better In-Context Models"☆159Updated 2 months ago
- Trying to build an all in one speech-text language model - a bit like GPT-4o☆22Updated 10 months ago