Downloads · 30 days
34
21% of all-time downloads
vadimbelsky/emirati-fastpitch-bilingual-v1.0
emirati-fastpitch-bilingual-v1.0 is a text-to-speech model from vadimbelsky. Use it when you need text read aloud. It is set up for nemo. The card lists the license as cc-by-4.0.
A fine-tuned FastPitch text-to-speech model for Emirati Arabic with Arabic–English bilingual code-switching support. Designed for natural prosody, dialectal Emirati pronunciation, and seamless AR/EN mixing in real-wor…
Downloads · 30 days
34
21% of all-time downloads
All-time downloads
165
Public
Repo size
185 MB
Likes
21
Public
Click a slice to open those files.
.nemo183 MB · 99%
From the Hugging Face model README
A fine-tuned FastPitch text-to-speech model for Emirati Arabic with Arabic–English bilingual code-switching support.
Designed for natural prosody, dialectal Emirati pronunciation, and seamless AR/EN mixing in real-world speech.
Reference text:
شو رأيك لو نعمل ورشة صغيرة للأطفال بالمدرسة عن الفنون اليدوية، ترى الأطفال يحبون الحركات هذي وبنشجعهم على الإبداع، إنت موافق تساعدنا بالمواد والأفكار ولا مب فاضي
Reference text:
اليوم جلسنا وقسمنا المهام في الـ Project Management عشان نحافظ على المحميات، الـ AI يساعد في رصد الحيوانات والطيور والـ Dashboard يعطينا تنبيهات، شو تتوقعون بيصير لو ما سوينا Update سريع، ترى الوضع مهم وايد
Reference text:
Basically, pair programming feels awkward at first, but you know, it actually speeds up problem solving and learning
💡 All samples were synthesized using Emirati FastPitch v1.0 + Emirati HiFi-GAN bilingual vocoder at 22,050 Hz.
| Item | Value |
|---|---|
| Model Type | FastPitch |
| Framework | NVIDIA NeMo |
| Sample Rate | 22,050 Hz |
| Epochs | 1,059 |
| Training Data | 10+ hours (Emirati Arabic + English) |
| Phoneme Inventory | 200+ AR_/EN_ tokens |
This model is designed to be used with:
Emirati HiFi-GAN Bilingual v1.0
https://huggingface.co/vadimbelsky/emirati-hifigan-bilingual-v1.0
The vocoder is trained on matching mel-spectrogram configuration, ensuring:
from nemo.collections.tts.models import FastPitchModel
fastpitch = FastPitchModel.from_pretrained(
"vadimbelsky/emirati-fastpitch-bilingual-v1.0"
)
fastpitch.eval()
from emirati_phoneme_converter import EmiratiPhonemeConverter
converter = EmiratiPhonemeConverter()
phonemes = converter.convert(
"اليوم عندنا meeting مهم with the AI team"
)
tokens = fastpitch.parse(phonemes)
mel = fastpitch.generate_spectrogram(tokens=tokens)
from nemo.collections.tts.models import HifiGanModel
vocoder = HifiGanModel.from_pretrained(
"vadimbelsky/emirati-hifigan-bilingual-v1.0"
)
vocoder.eval()
audio = vocoder.convert_spectrogram_to_audio(mel)
🌍 Supported Languages • Emirati Arabic (dialect) • English (US-style phonemes) • Mixed Arabic–English speech (code-switching)
📜 License
This model is released under CC-BY-4.0.
📌 Citation
Emirati FastPitch v1.0 – Bilingual Emirati Arabic TTS Vadim Belsky, 2026