metadata

language:
  - 'no'
license: apache-2.0
base_model: NbAiLabBeta/nb-whisper-medium
tags:
  - audio
  - asr
  - automatic-speech-recognition
  - hf-asr-leaderboard
model-index:
  - name: nb-whisper-medium-v0.7-semantic
    results: []

nb-whisper-medium-v0.7-semantic

This model is a fine-tuned version of NbAiLabBeta/nb-whisper-medium on the NbAiLab/ncc_speech_styling_v4 dataset.

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 2.5e-05
lr_scheduler_type: linear
per_device_train_batch_size: 32
total_train_batch_size_per_node: 128
total_train_batch_size: 1024
total_optimization_steps: 250
starting_optimization_step: None
finishing_optimization_step: 250
num_train_dataset_workers: 32
num_hosts: 8
total_num_training_examples: 256,000
steps_per_epoch: To be computed after first epoch
num_beams: None
weight_decay: 0.01
adam_beta1: 0.9
adam_beta2: 0.98
adam_epsilon: 1e-06
dropout: True
bpe_dropout_probability: 0.2
activation_dropout_probability: 0.1

Training results

step	validation_nst_loss	train_loss	validation_nst_wer	validation_nst_cer	validation_nst_exact_wer	validation_nst_exact_cer	validation_clean_stortinget_no_loss	validation_clean_stortinget_no_wer	validation_clean_stortinget_no_cer	validation_clean_stortinget_no_exact_wer	validation_clean_stortinget_no_exact_cer
0	0.4372	1.1581	2.2865	0.7038	2.9452	0.8059	0.7951	8.8939	5.6567	11.9393	6.1348
40	0.7551	0.7309	2.7546	0.9443	3.4950	1.0568	0.7489	9.8437	6.4691	12.9830	6.9559
80	0.7655	0.6341	2.5695	0.8250	3.3317	0.9414	0.7355	9.3794	6.1000	12.4090	6.5664
120	0.7493	0.6262	2.4716	0.8129	3.2283	0.9286	0.7432	9.3344	6.0544	12.3592	6.5247

Framework versions

Transformers 4.34.1
Datasets 2.15.0
Tokenizers 0.14.1