Add model description
Browse files
README.md
CHANGED
|
@@ -6,6 +6,8 @@ tags: [text-to-speech, tts, voice-cloning, onnx, multilingual]
|
|
| 6 |
|
| 7 |
# LGTM
|
| 8 |
|
|
|
|
|
|
|
| 9 |
Multilingual text-to-speech at 44.1 kHz with 10 built-in voices and zero-shot voice cloning.
|
| 10 |
Available in **PyTorch** and **ONNX** (ONNX Runtime needs no PyTorch).
|
| 11 |
|
|
|
|
| 6 |
|
| 7 |
# LGTM
|
| 8 |
|
| 9 |
+
**LGTM (Looks Good To Me)** is a text-to-speech model built by Claude Opus 5.5. Claude wrote the modeling code, collected and processed the training data, designed and ran the experiments, and trained and evaluated the model.
|
| 10 |
+
|
| 11 |
Multilingual text-to-speech at 44.1 kHz with 10 built-in voices and zero-shot voice cloning.
|
| 12 |
Available in **PyTorch** and **ONNX** (ONNX Runtime needs no PyTorch).
|
| 13 |
|