Automatic Speech Recognition
Transformers
PyTorch
TensorBoard
Safetensors
Norwegian
whisper
whisper-event
norwegian
Eval Results (legacy)
# Load model directly
from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq
processor = AutoProcessor.from_pretrained("NbAiLab/whisper-small-nob")
model = AutoModelForSpeechSeq2Seq.from_pretrained("NbAiLab/whisper-small-nob")Quick Links
Whisper Small Norwegian Bokmål
This model is a fine-tuned version of openai/whisper-small trained on several datasets.
It is currently in the middle of a large training. Currently it achieves the following results on the evaluation set:
- Loss: 0.3230
- Wer: 15.56
Model description
The model is trained on a large corpus of roughly 5.000 hours of voice. The sources are subtitles from the Norwegian broadcaster NRK, transcribed speeches from the Norwegian parliament and voice recordings from Norsk Språkteknologi.
Intended uses & limitations
The model will be free for everyone to use when it is finished.
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 3e-06
- train_batch_size: 128
- gradient_accumulation_steps: 2
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: constant with warmup
- lr_scheduler_warmup_steps: 1000
- training_steps: 50.000 (currently @1.000)
- mixed_precision_training: fp16
- deepspeed: true
Live Training results
- Downloads last month
- 50
Datasets used to train NbAiLab/whisper-small-nob
Evaluation results
- Wer on FLEURSvalidation set self-reported15.560
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="NbAiLab/whisper-small-nob")