Automatic Speech Recognition
Transformers
PyTorch
Belarusian
wav2vec2
audio
speech
Eval Results (legacy)
Instructions to use ales/wav2vec2-cv-be with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use ales/wav2vec2-cv-be with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="ales/wav2vec2-cv-be")# Load model directly from transformers import AutoProcessor, AutoModelForCTC processor = AutoProcessor.from_pretrained("ales/wav2vec2-cv-be") model = AutoModelForCTC.from_pretrained("ales/wav2vec2-cv-be", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -60,5 +60,5 @@ This page contains interactive demo widget that lets you test this model right i
|
|
| 60 |
|
| 61 |
However, this widget uses Acoustic model only **without** Language model that significantly improves overall performance.
|
| 62 |
|
| 63 |
-
You can play with **full pipeline of Acoustic model + Language model** on the following [spaces page](https://huggingface.co/spaces/ales/wav2vec2-cv-be-lm
|
| 64 |
(also works from browser).
|
|
|
|
| 60 |
|
| 61 |
However, this widget uses Acoustic model only **without** Language model that significantly improves overall performance.
|
| 62 |
|
| 63 |
+
You can play with **full pipeline of Acoustic model + Language model** on the following [spaces page](https://huggingface.co/spaces/ales/wav2vec2-cv-be-lm)
|
| 64 |
(also works from browser).
|