Document Space URL, upstream duplicate, link notmax123/blue
Browse files
README.md
CHANGED
|
@@ -12,8 +12,12 @@ python_version: "3.12"
|
|
| 12 |
|
| 13 |
# BlueTTS — Multilingual text-to-speech
|
| 14 |
|
|
|
|
|
|
|
| 15 |
Interactive demo for **[BlueTTS](https://github.com/maxmelichov/BlueTTS)**: fast on-device synthesis with **ONNX Runtime**. Type text, pick a language and voice, and generate audio in the browser. Project site: [lightbluetts.com](https://lightbluetts.com/).
|
| 16 |
|
|
|
|
|
|
|
| 17 |
## Languages
|
| 18 |
|
| 19 |
- **English, Spanish, German, Italian** — phonemization with **espeak-ng** (via phonemizer), aligned with the multilingual tokenizer in the app.
|
|
@@ -36,11 +40,15 @@ This Space runs **inference from `app.py`** (vocabulary, phonemization, ONNX ses
|
|
| 36 |
|
| 37 |
ONNX checkpoints are **not** stored in this Space repo (file-size limits). On first startup, `download_models.py` fetches them from the public model repo **[notmax123/blue-onnx](https://huggingface.co/notmax123/blue-onnx)** into `./onnx_models/`.
|
| 38 |
|
|
|
|
|
|
|
| 39 |
If you fork this Space and point downloads at a **private** repo, set a Hugging Face **write** token as the Space secret `HF_TOKEN` so authenticated downloads still work.
|
| 40 |
|
| 41 |
## Links
|
| 42 |
|
|
|
|
| 43 |
- **ONNX weights:** [notmax123/blue-onnx](https://huggingface.co/notmax123/blue-onnx)
|
|
|
|
| 44 |
- **Source code:** [maxmelichov/BlueTTS on GitHub](https://github.com/maxmelichov/BlueTTS)
|
| 45 |
- **Hebrew G2P:** [thewh1teagle/renikud](https://huggingface.co/thewh1teagle/renikud)
|
| 46 |
|
|
|
|
| 12 |
|
| 13 |
# BlueTTS — Multilingual text-to-speech
|
| 14 |
|
| 15 |
+
**This Space:** [https://huggingface.co/spaces/notmax123/Blue](https://huggingface.co/spaces/notmax123/Blue)
|
| 16 |
+
|
| 17 |
Interactive demo for **[BlueTTS](https://github.com/maxmelichov/BlueTTS)**: fast on-device synthesis with **ONNX Runtime**. Type text, pick a language and voice, and generate audio in the browser. Project site: [lightbluetts.com](https://lightbluetts.com/).
|
| 18 |
|
| 19 |
+
This Space was duplicated from [thewh1teagle/lightblue-tts-hebrew](https://huggingface.co/spaces/thewh1teagle/lightblue-tts-hebrew) and adapted for the current BlueTTS ONNX bundle.
|
| 20 |
+
|
| 21 |
## Languages
|
| 22 |
|
| 23 |
- **English, Spanish, German, Italian** — phonemization with **espeak-ng** (via phonemizer), aligned with the multilingual tokenizer in the app.
|
|
|
|
| 40 |
|
| 41 |
ONNX checkpoints are **not** stored in this Space repo (file-size limits). On first startup, `download_models.py` fetches them from the public model repo **[notmax123/blue-onnx](https://huggingface.co/notmax123/blue-onnx)** into `./onnx_models/`.
|
| 42 |
|
| 43 |
+
**Training / finetuning / voice-export weights** (PyTorch / Safetensors): **[notmax123/blue](https://huggingface.co/notmax123/blue)**.
|
| 44 |
+
|
| 45 |
If you fork this Space and point downloads at a **private** repo, set a Hugging Face **write** token as the Space secret `HF_TOKEN` so authenticated downloads still work.
|
| 46 |
|
| 47 |
## Links
|
| 48 |
|
| 49 |
+
- **This demo (Space):** [huggingface.co/spaces/notmax123/Blue](https://huggingface.co/spaces/notmax123/Blue)
|
| 50 |
- **ONNX weights:** [notmax123/blue-onnx](https://huggingface.co/notmax123/blue-onnx)
|
| 51 |
+
- **PyTorch / training weights:** [notmax123/blue](https://huggingface.co/notmax123/blue)
|
| 52 |
- **Source code:** [maxmelichov/BlueTTS on GitHub](https://github.com/maxmelichov/BlueTTS)
|
| 53 |
- **Hebrew G2P:** [thewh1teagle/renikud](https://huggingface.co/thewh1teagle/renikud)
|
| 54 |
|