Update README.md

README.md

@@ -1,45 +1,51 @@
 ---
 license: apache-2.0
 language:
-- it
-- en
-- pl
-- de
-- fr
+  - it
+  - en
+  - pl
+  - de
+  - fr
 base_model:
-- nari-labs/Dia-1.6B
+  - nari-labs/Dia-1.6B
 pipeline_tag: text-to-speech
 tags:
-- speech
-- dia
-- text-to-speech
-- vocal
-- voice
+  - speech
+  - dia
+  - text-to-speech
+  - vocal
+  - voice
 ---
-# Multilingual Emotion TTS Model
 
-A fine-tuned version of Dia-1.6B trained on multilingual datasets.
+# Aurora-1.6B: Multilingual Emotion and Singing TTS Model
+
+A fine-tuned version of Dia-1.6B trained on multilingual and singing datasets, with full emotion control and zero-shot voice cloning.
 
 ## Features
 
-- Support for multiple languages
-- Emotion control in speech generation
-- Singing capabilities
+- **Multilingual Support**  
+  Natural speech in Italian, English, Polish, German, French, and more.  
+- **Emotion Control**  
+  Use speaker tags or emotion tokens (e.g. `[S1]`, `[happy]`, `[sad]`) to modulate expressiveness.  
+- **Singing Capabilities**  
+  Generate melodic vocals by providing singing prompts or style references.  
+- **Zero-Shot Voice Cloning**  
+  Clone any speaker’s voice from a short audio sample.  
+- **Nonverbal Vocalizations**  
+  Embed realistic effects like `(laughs)`, `(coughs)`, or `(sighs)` inline.
 
 ## Usage
 
 ```python
 from dia.model import Dia
-import torch
+import soundfile as sf
 
-# Carica il modello personalizzato
+# Load the Aurora-1.6B model
 model = Dia.from_pretrained("Lorenzob/aurora-1.6b")
 
-# Genera audio con emozione
-text = "[S1] Say 'Hello world' with a happy emotion"
-output = model.generate(text)
+# Generate a happy spoken line followed by singing
+text = "[S1][happy] Hello world! Now sing 'Happy Birthday to You'"
+audio = model.generate(text)
 
-# Salva l'audio
-import soundfile as sf
-sf.write("output.mp3", output, 44100)
-```
+# Save output at 44.1 kHz
+sf.write("output.wav", audio, 44100)