VikhrModels / Salt
☆42Updated 2 weeks ago
Alternatives and similar repositories for Salt
Users that are interested in Salt are comparing it to the libraries listed below
Sorting:
- T5-based (russian) text normalization☆20Updated last year
- Простой IPA фонемизатор на базе ruaccent-encoder☆20Updated last month
- Framework for processing and filtering datasets☆27Updated 9 months ago
- Normalize Text in Russian☆28Updated last year
- Простой нормализатор текстов перед синтезом речи☆32Updated last year
- ☆31Updated 7 months ago
- Automatic Speech Recognition in Python using ONNX models☆23Updated this week
- Use quantized versions of Whisper to speed up inference☆12Updated 7 months ago
- Simple audio AE☆12Updated 6 months ago
- Official repository of Wavehax vocoder☆46Updated 5 months ago
- Modified Arena-Hard-Auto LLM evaluation toolkit with an emphasis on Russian language☆42Updated last month
- Open TTS models, built for streaming on the edge☆41Updated 2 months ago
- ☆26Updated last week
- Top ML papers of the week.☆31Updated this week
- RuBLiMP: Russian Benchmark of Linguistic Minimal Pairs☆17Updated 3 months ago
- Effective LLM Alignment Toolkit☆130Updated last month
- ☆46Updated 3 weeks ago
- Code associated with the paper: CTC-DRO: Robust Optimization for Reducing Language Disparities in Speech Recognition.☆14Updated 2 months ago
- ☆22Updated last year
- Legible, Scalable, Reproducible Foundation Models with Named Tensors and Jax☆14Updated 11 months ago
- ☆62Updated 9 months ago
- MERA (Multimodal Evaluation for Russian-language Architectures) is a new open benchmark for the Russian language for evaluating SOTA mode…☆25Updated last month
- Provide Gradio custom components to make the diarization-based audio labeling process easier and faster.☆62Updated last month
- StyleTTS 2 Optimized Training Fork☆28Updated 3 months ago
- Trying to build an all in one speech-text language model - a bit like GPT-4o☆22Updated 11 months ago
- ☆13Updated 8 months ago
- ☆18Updated last month
- GPT-style network for phonemization with durations of text☆64Updated last year
- Joint speech-language model - respond directly to audio!☆30Updated last year
- MERA (Multimodal Evaluation for Russian-language Architectures) is a new open benchmark for the Russian language for evaluating fundament…☆62Updated 7 months ago