sovaai / sova-asrLinks
SOVA ASR (Automatic Speech Recognition)
☆173Updated 2 years ago
Alternatives and similar repositories for sova-asr
Users that are interested in sova-asr are comparing it to the libraries listed below
Sorting:
- ☆163Updated 2 years ago
- ☆129Updated 2 years ago
- Tacotron2 based engine for the SOVA-TTS project☆66Updated 4 years ago
- NLP-preprocessor for the SOVA-TTS project☆53Updated 4 years ago
- Russian Speech Recognition system based on Mozilla's DeepSpeech TensorFlow implementation.☆82Updated 6 years ago
- ☆213Updated 4 years ago
- Deep Learning framework with NVIDIA & AMD support☆59Updated 2 years ago
- Russian text normalization pipeline for speech-to-text and other applications based on tagging s2s networks☆120Updated 4 years ago
- Accentor and transcriptor for Russian language☆127Updated 3 years ago
- ☆133Updated 4 months ago
- Russian speech technology links☆340Updated last month
- Проект д ля распознавания речи на русском языке на основе pykaldi.☆333Updated last year
- Text To Speech Synthesis with Vosk☆214Updated last month
- ☆58Updated 7 months ago
- 🇷🇺 Punctuation restoration production-ready model for Russian language 🇷🇺☆58Updated 4 years ago
- Open STT☆805Updated 3 years ago
- Tacotron2 + Waveglow Russian☆43Updated 5 years ago
- ☆32Updated 3 years ago
- Простой расстановщик ударений с обработкой омографов☆156Updated 11 months ago
- Распознавание речи русского языка используя Tensorflow, обучаясь на базе Voxforge☆58Updated 3 years ago
- Простая модель расстановки запятых на основе BERT☆40Updated 5 years ago
- Foundational Model for Speech Recognition Tasks☆293Updated last month
- Fine tuning of the base model from OpenAI Whisper in Russian language on the dataset Sber-golos☆40Updated 2 years ago
- python package russtress accentuates russian text☆57Updated 5 years ago
- Диалоговая система на базе FRED-T5☆37Updated 2 years ago
- An expanded version of the previously released Kazakh text-to-speech (KazakhTTS) synthesis corpus. In KazakhTTS2, the overall size has in…☆137Updated last month
- Emotions recognition from audio and text files (only russian language)☆75Updated 3 months ago
- T-one is a high-performance streaming ASR pipeline for Russian, specialized for the telephony domain.☆185Updated last month
- Creating Russian voice model for cmu-sphinx☆90Updated 9 years ago
- Проект для перевода чисел, записанных в текстовом виде на русском языке.☆104Updated 4 years ago