File size: 575 Bytes
43f8b09
a1952f5
32ae352
95ae54e
74f1fee
a1952f5
43f8b09
 
 
20ec756
91a938c
32ae352
8e9e688
74f1fee
 
32ae352
74f1fee
7a94b60
a1952f5
 
74f1fee
 
e142463
43f8b09
aa73355
43f8b09
aa73355
a1952f5
74f1fee
 
a1952f5
43f8b09
20ec756
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
# Core ML libraries
torch>=2.6.0
torchaudio>=2.1.0
transformers>=4.30.0
accelerate>=0.20.0

# FIXED: Pin pydantic to stable version to avoid Gradio crash
pydantic==2.10.6

# Updated versions for compatibility
gradio>=4.44.1
numpy>=1.21.0

# Audio processing
librosa>=0.10.0
soundfile>=0.12.0
scipy>=1.9.0

# Speech models
datasets>=2.14.0
peft>=0.6.0
safetensors>=0.3.0

# Dia TTS dependencies
descript-audio-codec>=1.0.0
huggingface_hub>=0.16.0

# Utilities
requests>=2.28.0
python-dotenv>=1.0.0

# Install Dia TTS directly from git
git+https://github.com/nari-labs/dia.git