miras-tech / MirasVoice
MirasVoice is a data set consisting speech samples from bilinguals to train neural network for optimization of speaker verification algorithms
☆17Updated 4 years ago
Related projects ⓘ
Alternatives and complementary repositories for MirasVoice
- fine-tune Wav2vec2. an ASR model released by Facebook☆37Updated 2 years ago
- Persian Consonant Vowel Combination (PCVC) Speech Dataset☆18Updated 3 years ago
- 🤗 ParsBERT Persian NER Tasks☆16Updated 3 years ago
- Persian Grapheme-to-Phoneme (G2P) converter☆39Updated 4 months ago
- a conversion of Dadegan corpus (first Persian dependency corpus) to the universal dependency version☆10Updated last week
- Open-source dependency parser, part-of-speech tagger, and text normalizer for Farsi (Persian)☆43Updated 10 years ago
- Tihu dictionary for Persian language☆12Updated 5 years ago
- Cross Platform Persian POS Tagger☆23Updated 6 years ago
- Beheshti-NER: Persian named entity recognition Using BERT☆14Updated 3 years ago
- Sharif Emotional Speech Database☆33Updated 3 years ago
- Zabanshenas is a solution for identifying the most likely language of a piece of written text. Demo (👇 )