Popular repositories Loading

1. ManaTTS-Persian-Speech-Dataset ManaTTS-Persian-Speech-Dataset Public

   ManaTTS is the largest open Persian speech dataset with 114+ hours of transcribed audio. Includes data collection pipeline and tools. Suitable for Persian text-to-speech models.

   Jupyter Notebook 59 5

2. LLM-Powered-G2P LLM-Powered-G2P Public

   Code and Resources for "LLM-Powered Grapheme-to-Phoneme Conversion: Benchmark and Case Study", introducing methods to leverage LLMs for G2P tasks without additional training, featuring Sentence-Ben…

   Jupyter Notebook 20 3

3. ManaTTS-Persian-Tacotron2-Model ManaTTS-Persian-Tacotron2-Model Public

   Tacotron2 Persian Text-to-Speech Model trained on ManaTTS, the largest open single-speaker Persian speech dataset with over 114 hours of high-quality audio.

   Jupyter Notebook 16 3

4. Piper-with-LCA-Phonemizer Piper-with-LCA-Phonemizer Public

   PiperTTS Enhanced with Lightweight Context-Aware Phonemizer

   C++ 16 2

5. GPTInformal-Persian-Speech-Dataset GPTInformal-Persian-Speech-Dataset Public

   A free licensed Persian TTS dataset including 6+ hours of audio-text pairs with subject

   13 2

6. Homo-GE2PE-Persian Homo-GE2PE-Persian Public

   A Persian grapheme-to-phoneme (G2P) model designed for homograph disambiguation, fine-tuned using the HomoRich dataset to improve pronunciation accuracy.

   Jupyter Notebook 11 2