Automatic Speech Recognition
Transformers
PyTorch
JAX
Safetensors
Kyrgyz
wav2vec2
audio
speech
xlsr-fine-tuning-week
Eval Results (legacy)
Instructions to use aismlv/wav2vec2-large-xlsr-kyrgyz with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use aismlv/wav2vec2-large-xlsr-kyrgyz with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="aismlv/wav2vec2-large-xlsr-kyrgyz")# Load model directly from transformers import AutoProcessor, AutoModelForCTC processor = AutoProcessor.from_pretrained("aismlv/wav2vec2-large-xlsr-kyrgyz") model = AutoModelForCTC.from_pretrained("aismlv/wav2vec2-large-xlsr-kyrgyz", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Xet hash:
- 2523581ab272a5438f25b3404df860e328c4479be1683a12e9e18d25874b1e66
- Size of remote file:
- 1.26 GB
- SHA256:
- 6462ccc7bc8d19ad1de00000e1008f854f69f341ace1211520a5733584abeefc
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.