Automatic Speech Recognition
Transformers
Safetensors
Northern Kurdish
wav2vec2-bert
kurdish
badini
kurmanji
low-resource
Instructions to use computeram/badini-w2v-bert with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use computeram/badini-w2v-bert with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="computeram/badini-w2v-bert")# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForCTC processor = AutoProcessor.from_pretrained("computeram/badini-w2v-bert") model = AutoModelForCTC.from_pretrained("computeram/badini-w2v-bert", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Upload README.md with huggingface_hub
Browse files
README.md
CHANGED
|
@@ -36,14 +36,6 @@ Kurmanji, written in Arabic script), fine-tuned from
|
|
| 36 |
[`facebook/w2v-bert-2.0`](https://huggingface.co/facebook/w2v-bert-2.0)
|
| 37 |
with a CTC head.
|
| 38 |
|
| 39 |
-
## Results
|
| 40 |
-
|
| 41 |
-
Evaluated on a held-out test set of **2,038** samples:
|
| 42 |
-
|
| 43 |
-
| Metric | Score |
|
| 44 |
-
|--------|--------|
|
| 45 |
-
| WER | 46.52% |
|
| 46 |
-
| CER | 12.03% |
|
| 47 |
|
| 48 |
## Input requirements
|
| 49 |
|
|
|
|
| 36 |
[`facebook/w2v-bert-2.0`](https://huggingface.co/facebook/w2v-bert-2.0)
|
| 37 |
with a CTC head.
|
| 38 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 39 |
|
| 40 |
## Input requirements
|
| 41 |
|