Update app.py
Browse files
app.py
CHANGED
@@ -18,7 +18,8 @@ MODELS = {
|
|
18 |
"amphion/MaskGCT": "MaskGCT",
|
19 |
"OuteAI/Llama-OuteTTS-1.0-1B": "Llama-OuteTTS-1.0-1B",
|
20 |
"ByteDance/MegaTTS3": "MegaTTS3",
|
21 |
-
"Kyutai/Kyutai-TTS": "Kyutai-TTS"
|
|
|
22 |
}
|
23 |
|
24 |
# Performance ratings for each model
|
@@ -36,6 +37,7 @@ MODEL_RATINGS = {
|
|
36 |
"OuteAI/Llama-OuteTTS-1.0-1B": {"naturalness": "Moderate", "intelligibility": "Moderate", "controllability": "Moderate"},
|
37 |
"ByteDance/MegaTTS3": {"naturalness": "Good", "intelligibility": "Good", "controllability": "Moderate"},
|
38 |
"Kyutai/Kyutai-TTS": {"naturalness": "Good", "intelligibility": "Good", "controllability": "Moderate"},
|
|
|
39 |
}
|
40 |
|
41 |
# Model descriptions for better understanding
|
@@ -52,7 +54,8 @@ MODEL_DESCRIPTIONS = {
|
|
52 |
"amphion/MaskGCT": "Masked generative modeling approach",
|
53 |
"OuteAI/Llama-OuteTTS-1.0-1B": "LLM-based TTS with moderate performance",
|
54 |
"ByteDance/MegaTTS3": "Industrial-grade TTS solution",
|
55 |
-
"Kyutai/Kyutai-TTS": "Industrial-grade TTS solution"
|
|
|
56 |
}
|
57 |
|
58 |
# Folder that contains subfolders with the audio clips
|
|
|
18 |
"amphion/MaskGCT": "MaskGCT",
|
19 |
"OuteAI/Llama-OuteTTS-1.0-1B": "Llama-OuteTTS-1.0-1B",
|
20 |
"ByteDance/MegaTTS3": "MegaTTS3",
|
21 |
+
"Kyutai/Kyutai-TTS": "Kyutai-TTS",
|
22 |
+
"ResembleAI/chatterbox":"chatterbox",
|
23 |
}
|
24 |
|
25 |
# Performance ratings for each model
|
|
|
37 |
"OuteAI/Llama-OuteTTS-1.0-1B": {"naturalness": "Moderate", "intelligibility": "Moderate", "controllability": "Moderate"},
|
38 |
"ByteDance/MegaTTS3": {"naturalness": "Good", "intelligibility": "Good", "controllability": "Moderate"},
|
39 |
"Kyutai/Kyutai-TTS": {"naturalness": "Good", "intelligibility": "Good", "controllability": "Moderate"},
|
40 |
+
"ResembleAI/chatterbox": {"naturalness": "Good", "intelligibility": "Good", "controllability": "Moderate"},
|
41 |
}
|
42 |
|
43 |
# Model descriptions for better understanding
|
|
|
54 |
"amphion/MaskGCT": "Masked generative modeling approach",
|
55 |
"OuteAI/Llama-OuteTTS-1.0-1B": "LLM-based TTS with moderate performance",
|
56 |
"ByteDance/MegaTTS3": "Industrial-grade TTS solution",
|
57 |
+
"Kyutai/Kyutai-TTS": "Industrial-grade TTS solution",
|
58 |
+
"ResembleAI/chatterbox":"Industrial-grade TTS solution",
|
59 |
}
|
60 |
|
61 |
# Folder that contains subfolders with the audio clips
|