Automatic Speech Recognition
Transformers
PyTorch
TensorBoard
Safetensors
wav2vec2
Eval Results (legacy)
Instructions to use NbAiLab/XLSR-300M-nynorsk with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use NbAiLab/XLSR-300M-nynorsk with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="NbAiLab/XLSR-300M-nynorsk")# Load model directly from transformers import AutoProcessor, AutoModelForCTC processor = AutoProcessor.from_pretrained("NbAiLab/XLSR-300M-nynorsk") model = AutoModelForCTC.from_pretrained("NbAiLab/XLSR-300M-nynorsk") - Notebooks
- Google Colab
- Kaggle
metadata
license: apache-2.0
tags:
- generated_from_trainer
- automatic-speech-recognition
- NbAiLab/NPSC
- robust-speech-event
- false
- nn-NO
- hf-asr-leaderboard
datasets:
- NbAiLab/NPSC
language:
- nn-NO
model-index:
- name: XLSR-300M-nynorsk
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: NPSC
type: NbAiLab/NPSC
args: 16K_mp3_nynorsk
metrics:
- name: Test (Nynorsk) WER
type: wer
value: 0.12136286840623241
- name: Test (Nynorsk) CER
type: cer
value: 0.041988362534453025