Update README.md
Browse files
README.md
CHANGED
|
@@ -60,23 +60,24 @@
|
|
| 60 |
- [x] Fastapi server and client
|
| 61 |
|
| 62 |
## Evaluation
|
| 63 |
-
| Model | CER (%) β
|
| 64 |
-
|
| 65 |
-
| Human | 1.26 | 2.14 | - |
|
| 66 |
-
|
|
| 67 |
-
|
|
| 68 |
-
|
|
| 69 |
-
|
|
| 70 |
-
|
|
| 71 |
-
|
|
| 72 |
-
|
|
| 73 |
-
|
|
| 74 |
-
|
|
| 75 |
-
|
|
| 76 |
-
|
|
| 77 |
-
| GLM-
|
| 78 |
-
|
|
| 79 |
-
| Fun-CosyVoice3-0.5B-
|
|
|
|
| 80 |
|
| 81 |
|
| 82 |
## Install
|
|
|
|
| 60 |
- [x] Fastapi server and client
|
| 61 |
|
| 62 |
## Evaluation
|
| 63 |
+
| Model | Open-Source | Model Size | test-zh<br>CER (%) β | test-zh<br>Speaker Similarity (%) β | test-en<br>WER (%) β | test-en<br>Speaker Similarity (%) β | test-hard<br>CER (%) β | test-hard<br>Speaker Similarity (%) |
|
| 64 |
+
| :--- | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: |
|
| 65 |
+
| Human | - | - | 1.26 | 75.5 | 2.14 | 73.4 | - | - |
|
| 66 |
+
| Seed-TTS | β | - | 1.12 | 79.6 | 2.25 | 76.2 | 7.59 | 77.6 |
|
| 67 |
+
| MiniMax-Speech | β | - | 0.83 | 78.3 | 1.65 | 69.2 | - | - |
|
| 68 |
+
| F5-TTS | β
| 0.3B | 1.52 | 74.1 | 2.00 | 64.7 | 8.67 | 71.3 |
|
| 69 |
+
| Spark TTS | β
| 0.5B | 1.2 | 66.0 | 1.98 | 57.3 | - | - |
|
| 70 |
+
| CosyVoice2 | β
| 0.5B | 1.45 | 75.7 | 2.57 | 65.9 | 6.83 | 72.4 |
|
| 71 |
+
| FireRedTTS 2 | β
| 1.5B | 1.14 | 73.2 | 1.95 | 66.5 | - | - |
|
| 72 |
+
| Index-TTS2 | β
| 1.5B | 1.03 | 76.5 | 2.23 | 70.6 | 7.12 | 75.5 |
|
| 73 |
+
| VibeVoice-1.5B | β
| 1.5B | 1.16 | 74.4 | 3.04 | 68.9 | - | - |
|
| 74 |
+
| VibeVoice-Realtime | β
| 0.5B | - | - | 2.05 | 63.3 | - | - |
|
| 75 |
+
| HiggsAudio-v2 | β
| 3B | 1.50 | 74.0 | 2.44 | 67.7 | - | - |
|
| 76 |
+
| VoxCPM | β
| 0.5B | 0.93 | 77.2 | 1.85 | 72.9 | 8.87 | 73.0 |
|
| 77 |
+
| GLM-TTS | β
| 1.5B | 1.03 | 76.1 | - | - | - | - |
|
| 78 |
+
| GLM-TTS RL | β
| 1.5B | 0.89 | 76.4 | - | - | - | - |
|
| 79 |
+
| Fun-CosyVoice3-0.5B-2512 | β
| 1.5B | 0.89 | 76.4 | - | - | - | - |
|
| 80 |
+
|
| 81 |
|
| 82 |
|
| 83 |
## Install
|