metadata

language:
  - 'no'
license: apache-2.0
tags:
  - audio
  - asr
  - automatic-speech-recognition
  - hf-asr-leaderboard
model-index:
  - name: scream_non_large_3e06_beams5_v2
    results: []

scream_non_large_3e06_beams5_v2

This model is a fine-tuned version of openai/whisper-large-v2 on the NbAiLab/NCC_speech_all_v5 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: 3e-06
lr_scheduler_type: linear
per_device_train_batch_size: 5
total_train_batch_size_per_node: 20
total_train_batch_size: 160
total_optimization_steps: 30,000
starting_optimization_step: None
finishing_optimization_step: 30,000
num_train_dataset_workers: 32
numb_hosts: 8
total_num_training_examples: 4,800,000
steps_per_epoch: To be computed after first epoch
num_beams: 5

Training results

step	eval_loss	train_loss	eval_wer	eval_cer
0	2.0006	0.8864	15.7125	8.0675

Framework versions

Transformers 4.29.0.dev0
Datasets 2.11.0
Tokenizers 0.13.3