Automatic Speech Recognition
Transformers
PyTorch
Armenian
Armenian
multilingual
wav2vec2
mozilla-foundation/common_voice_9_0
google/fleurs
Instructions to use YSU/aspram with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use YSU/aspram with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="YSU/aspram")# Load model directly from transformers import AutoProcessor, AutoModelForCTC processor = AutoProcessor.from_pretrained("YSU/aspram") model = AutoModelForCTC.from_pretrained("YSU/aspram") - Notebooks
- Google Colab
- Kaggle
metadata
language:
- hy
- hye
- multilingual
license: apache-2.0
tags:
- automatic-speech-recognition
- hy
- mozilla-foundation/common_voice_9_0
- google/fleurs
datasets:
- mozilla-foundation/common_voice_9_0
- google/fleurs
- mc4
models:
- facebook/wav2vec2-xls-r-2b
task_categories:
- automatic-speech-recognition
- speech-processing
task_ids:
- speech-recognition
Automatic SPeech Recognition for ArMenian
TODO Model details