Upload folder using huggingface_hub

README.md

@@ -1,3 +1,27 @@
----
-license: apache-2.0
----
+# Multilingual Emotion TTS Model
+
+A fine-tuned version of Dia-1.6B trained on multilingual datasets.
+
+## Features
+
+- Support for multiple languages
+- Emotion control in speech generation
+- Singing capabilities
+
+## Usage
+
+```python
+from dia.model import Dia
+import torch
+
+# Carica il modello personalizzato
+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)
+
+# Salva l'audio
+import soundfile as sf
+sf.write("output.mp3", output, 44100)
+```

dia_multilingual_model.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a0c6599886863c6135855bf33b8e884eda4ed717e66f0b4fa228b54e7d17c6b
+size 3222742169

model_info.json

@@ -0,0 +1,4 @@
+{
+  "description": "Fine-tuned Dia-1.6B model for multilingual TTS",
+  "base_model": "nari-labs/Dia-1.6B"
+}

model_state_dict.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c11035b70ed3142d63f5717c6d0c28de97da3e259639745c616d11235c6c2a70
+size 3222740023