Text-to-Speech
Chatterbox
Safetensors
Arabic
Saudi
Arabic
Saudi-Dialect
Chatterbox
TTS
voice-cloning
multilingual-tts
Instructions to use NAMAA-Space/NAMAA-Saudi-TTS with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Chatterbox
How to use NAMAA-Space/NAMAA-Saudi-TTS with Chatterbox:
# pip install chatterbox-tts import torchaudio as ta from chatterbox.tts import ChatterboxTTS model = ChatterboxTTS.from_pretrained(device="cuda") text = "Ezreal and Jinx teamed up with Ahri, Yasuo, and Teemo to take down the enemy's Nexus in an epic late-game pentakill." wav = model.generate(text) ta.save("test-1.wav", wav, model.sr) # If you want to synthesize with a different voice, specify the audio prompt AUDIO_PROMPT_PATH="YOUR_FILE.wav" wav = model.generate(text, audio_prompt_path=AUDIO_PROMPT_PATH) ta.save("test-2.wav", wav, model.sr) - Notebooks
- Google Colab
- Kaggle
Observations on the audio output
#1
by mobeidat - opened
Thanks for the excellent work on this. I tested and it works great, have the following observations:\
- I tested with a few examples that I have other models struggle with but it read them correctly some thing like 'الإعدادات', 'لهذا', etc...
- It does not speak digits correctly. I tried with Arabic numerals and Hindi numerals. Arabic numerals are spoken a bit better than Hindi but both are not understandable.
- It speaks too fast. I reduced cfg_weight to 0.1 but still faster than normal speech
thanks for the feedback, we work on second version of tther model where we are willing to solve these issues..
Omartificial-Intelligence-Space changed discussion status to closed