Delete README.md
Browse files
README.md
DELETED
|
@@ -1,38 +0,0 @@
|
|
| 1 |
-
---
|
| 2 |
-
title: Quantized_lang._Translator
|
| 3 |
-
app_file: app.py
|
| 4 |
-
sdk: gradio
|
| 5 |
-
sdk_version: 5.48.0
|
| 6 |
-
---
|
| 7 |
-
# NLLB-FB Language Translator (Quantized, CPU-Friendly)
|
| 8 |
-
|
| 9 |
-
This project provides a quantized, CPU-optimized version of the NLLB (No Language Left Behind) Facebook language translation model. It enables very fast inference on CPUs for translating between a wide variety of languages.
|
| 10 |
-
|
| 11 |
-
## Features
|
| 12 |
-
|
| 13 |
-
- **Quantized Model:** Reduced model size for efficient CPU usage.
|
| 14 |
-
- **Fast Inference:** Optimized for low-latency translation on standard CPUs.
|
| 15 |
-
- **Multi-language Support:** Translate between many language pairs.
|
| 16 |
-
- **Easy Integration:** Simple API for batch and single-sentence translation.
|
| 17 |
-
|
| 18 |
-
## Usage
|
| 19 |
-
|
| 20 |
-
1. **Install dependencies:**
|
| 21 |
-
```bash
|
| 22 |
-
pip install torch transformers
|
| 23 |
-
```
|
| 24 |
-
|
| 25 |
-
2. **Run the Gradio app:**
|
| 26 |
-
```bash
|
| 27 |
-
python app.py
|
| 28 |
-
```
|
| 29 |
-
|
| 30 |
-
|
| 31 |
-
## Supported Languages
|
| 32 |
-
|
| 33 |
-
See the [NLLB-200 language list](https://github.com/facebookresearch/fairseq/tree/main/examples/nllb) for all supported languages.
|
| 34 |
-
|
| 35 |
-
## References
|
| 36 |
-
|
| 37 |
-
- [NLLB: No Language Left Behind](https://ai.facebook.com/research/no-language-left-behind/)
|
| 38 |
-
- [Transformers Documentation](https://huggingface.co/docs/transformers/model_doc/nllb)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|