Open-source State-of-the-art TTS model which runs on a CPU 😻
Python
Update README.md
Kittend737634c7b91
diff --git a/README.md b/README.mdindex d83c0da..c074c64 100644--- a/README.md+++ b/README.md@@ -124,8 +124,8 @@ import soundfile as sfm = KittenTTS("KittenML/kitten-tts-2")-audio = m.generate("One day, a little girl named Lily found a needle in her room.",- voice="Bruno")+audio = m.generate("Hi! umm.. how are you, I guess? .. uh.. nice to meet you??",+ voice="WeatherPresenterCheerful")sf.write("output.wav", audio, m.sample_rate)```> To run Kitten-TTS 2 on a CPU, please refer to [Running on CPU](#running-on-cpu)@@ -145,7 +145,7 @@ m = KittenTTS("KittenML/kitten-tts-2", weights="emb4") # half the download```python# Trade stability against expressiveness-audio = m.generate("Hello, world.", voice="Luna", preset="expressive")+audio = m.generate("Hello, world.", voice="Matthew", preset="expressive")# Save directly to a filem.generate_to_file("Hello, world.", "output.wav", voice="Bruno")