Instructions to use b1n1yam/qwen3-asr-0.6b-amharic-gold-silver with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use b1n1yam/qwen3-asr-0.6b-amharic-gold-silver with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="b1n1yam/qwen3-asr-0.6b-amharic-gold-silver")# Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("b1n1yam/qwen3-asr-0.6b-amharic-gold-silver") model = AutoModelForMultimodalLM.from_pretrained("b1n1yam/qwen3-asr-0.6b-amharic-gold-silver", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Link Colab demo
Browse files
README.md
CHANGED
|
@@ -37,6 +37,12 @@ Lower WER and CER are better.
|
|
| 37 |
The curated variant is stronger on the curated-source heldout. The broader
|
| 38 |
mixed variant generalizes better to WAXAL in this evaluation.
|
| 39 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 40 |
## Usage
|
| 41 |
|
| 42 |
```bash
|
|
|
|
| 37 |
The curated variant is stronger on the curated-source heldout. The broader
|
| 38 |
mixed variant generalizes better to WAXAL in this evaluation.
|
| 39 |
|
| 40 |
+
## Live Colab Demo
|
| 41 |
+
|
| 42 |
+
[Open the Gradio demo notebook](https://huggingface.co/b1n1yam/qwen3-asr-0.6b-amharic-gold-silver/blob/main/colab_demo.ipynb),
|
| 43 |
+
then open it in Google Colab and run the cells in order. The final cell creates
|
| 44 |
+
a temporary public Gradio link while the notebook remains connected.
|
| 45 |
+
|
| 46 |
## Usage
|
| 47 |
|
| 48 |
```bash
|