erdemtuna/normalizer-tr

Ahenk: açık Türkçe metinden sese. Open Turkish text-to-speech: VoxCPM2 LoRA (Ahenk), 8.6M on-device model (Ahenk Cep), trnorm text normaliser, TR-Zor benchmark

Tiny, fast and accurate Turkish text-to-speech. 8.6M parameters, 0.92% WER on Freya-TR-Eval, first audio in ~4 ms and 1,300× real time on one GPU. Streams audio, batches many callers on one GPU, and runs offline on a GPU or CPU.

One-step Turkish text-to-speech trained with a drifting objective (Kyutai learned-temperature recipe)

Turkish voice design with VoxCPM2 on a 4 GB GPU: describe a voice, pick a variant, read Turkish text. Patched audio.cpp, local UI, 7 synthetic voices.

A python package for whisper normalizer

NLP tools for Turkish.

NeMo text processing for ASR and TTS

Turkish deasciifier in Python based on Deniz Yüret's turkish-mode for Emacs

Tarayıcıda çalışan Türkçe konuşma tanıma ve altyazı aracı. Otomatik noktalama, canlı transkript ve altyazılı video dışa aktarma. Tamamen yerel, WebGPU destekli.