Automatic Speech Recognition
Transformers
Safetensors
Ukrainian
wav2vec2-bert
audio
Eval Results (legacy)
Instructions to use speech-uk/w2v-bert with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use speech-uk/w2v-bert with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="speech-uk/w2v-bert")# Load model directly from transformers import AutoProcessor, AutoModelForCTC processor = AutoProcessor.from_pretrained("speech-uk/w2v-bert") model = AutoModelForCTC.from_pretrained("speech-uk/w2v-bert") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -35,6 +35,9 @@ model-index:
|
|
| 35 |
|
| 36 |
# w2v-bert-uk `v2.1`
|
| 37 |
|
|
|
|
|
|
|
|
|
|
| 38 |
|
| 39 |
## Community
|
| 40 |
|
|
@@ -43,7 +46,3 @@ model-index:
|
|
| 43 |
- Speech Synthesis: https://t.me/speech_synthesis_uk
|
| 44 |
|
| 45 |
See other Ukrainian models: https://github.com/egorsmkv/speech-recognition-uk
|
| 46 |
-
|
| 47 |
-
## Overview
|
| 48 |
-
|
| 49 |
-
This is the model - https://huggingface.co/Yehor/w2v-bert-uk-v2.1 - where tensors are saved in BF16 format.
|
|
|
|
| 35 |
|
| 36 |
# w2v-bert-uk `v2.1`
|
| 37 |
|
| 38 |
+
## Overview
|
| 39 |
+
|
| 40 |
+
This is the model - https://huggingface.co/Yehor/w2v-bert-uk-v2.1 - where tensors are saved in BF16 format.
|
| 41 |
|
| 42 |
## Community
|
| 43 |
|
|
|
|
| 46 |
- Speech Synthesis: https://t.me/speech_synthesis_uk
|
| 47 |
|
| 48 |
See other Ukrainian models: https://github.com/egorsmkv/speech-recognition-uk
|
|
|
|
|
|
|
|
|
|
|
|