Automatic Speech Recognition
Transformers
Safetensors
Russian
wav2vec2
speech
phoneme-recognition
russian
Instructions to use ViktorR-BarreL/phonoscopic with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use ViktorR-BarreL/phonoscopic with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="ViktorR-BarreL/phonoscopic")# Load model directly from transformers import AutoProcessor, AutoModelForCTC processor = AutoProcessor.from_pretrained("ViktorR-BarreL/phonoscopic") model = AutoModelForCTC.from_pretrained("ViktorR-BarreL/phonoscopic") - Notebooks
- Google Colab
- Kaggle
- Xet hash:
- 2cbb0404c4972c1cfbca6cd162bd74d141ac2d6d818f27f6b12b0c9910400b92
- Size of remote file:
- 5.14 kB
- SHA256:
- f68d0275f6bc2935e28656e549a44b4dce39b7901e84c887a06642c7495d84a0
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.