Instructions to use badrex/Ethio-ASR-multilingual-1B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use badrex/Ethio-ASR-multilingual-1B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="badrex/Ethio-ASR-multilingual-1B")# Load model directly from transformers import AutoProcessor, AutoModelForCTC processor = AutoProcessor.from_pretrained("badrex/Ethio-ASR-multilingual-1B") model = AutoModelForCTC.from_pretrained("badrex/Ethio-ASR-multilingual-1B", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -35,7 +35,7 @@ tags:
|
|
| 35 |
|
| 36 |
## ⚒️ Model Description
|
| 37 |
|
| 38 |
-
Ethio-ASR is a suite of multilingual Automatic Speech Recognition (ASR) models that support five Ethiopian languages:
|
| 39 |
The ASR model in this repo is based on the [mms-1b](https://huggingface.co/facebook/mms-1b) pre-trained model by fine-tuning it on the [WAXAL Speech Dataset](https://huggingface.co/datasets/google/WaxalNLP).
|
| 40 |
|
| 41 |
- **Developed by:** Ethio-ASR Team
|
|
|
|
| 35 |
|
| 36 |
## ⚒️ Model Description
|
| 37 |
|
| 38 |
+
Ethio-ASR is a suite of multilingual Automatic Speech Recognition (ASR) models that support five Ethiopian languages: Amharic, Tigrinya, Afaan Oromo, Sidama, and Wolaytta.
|
| 39 |
The ASR model in this repo is based on the [mms-1b](https://huggingface.co/facebook/mms-1b) pre-trained model by fine-tuning it on the [WAXAL Speech Dataset](https://huggingface.co/datasets/google/WaxalNLP).
|
| 40 |
|
| 41 |
- **Developed by:** Ethio-ASR Team
|