Instructions to use classla/wav2vec2-large-slavic-parlaspeech-hr with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use classla/wav2vec2-large-slavic-parlaspeech-hr with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="classla/wav2vec2-large-slavic-parlaspeech-hr")# Load model directly from transformers import AutoProcessor, AutoModelForCTC processor = AutoProcessor.from_pretrained("classla/wav2vec2-large-slavic-parlaspeech-hr") model = AutoModelForCTC.from_pretrained("classla/wav2vec2-large-slavic-parlaspeech-hr", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -17,7 +17,14 @@ widget:
|
|
| 17 |
|
| 18 |
# wav2vec2-large-slavic-parlaspeech-hr
|
| 19 |
|
| 20 |
-
This model for Croatian ASR is based on the
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 21 |
|
| 22 |
If you use this model, please cite the following paper:
|
| 23 |
|
|
|
|
| 17 |
|
| 18 |
# wav2vec2-large-slavic-parlaspeech-hr
|
| 19 |
|
| 20 |
+
This model for Croatian ASR is based on the
|
| 21 |
+
[facebook/wav2vec2-large-slavic-voxpopuli-v2 model](https://huggingface.co/facebook/wav2vec2-large-slavic-voxpopuli-v2)
|
| 22 |
+
and was fine-tuned with 300 hours of recordings and transcripts from the ASR Croatian parliament
|
| 23 |
+
dataset [ParlaSpeech-HR v1.0](http://hdl.handle.net/11356/1494).
|
| 24 |
+
|
| 25 |
+
<div style="border: 5px solid #ff6700; padding: 10px; margin: 10px 0;">
|
| 26 |
+
<strong>Notice:</strong> ParlaSpeech corpora are currently in the process of enrichment with new features. Follow our progress here: <a href="http://clarinsi.github.io/parlaspeech">http://clarinsi.github.io/parlaspeech</a>
|
| 27 |
+
</div>
|
| 28 |
|
| 29 |
If you use this model, please cite the following paper:
|
| 30 |
|