README.md

metadata

language:
  - 'no'
license: apache-2.0
tags:
  - audio
  - asr
  - automatic-speech-recognition
  - hf-asr-leaderboard
model-index:
  - name: scream_tertius_dropout_replicate_test7a
    results: []

scream_tertius_dropout_replicate_test7a

This model is a fine-tuned version of openai/whisper-small 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: 2e-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: 20,000
• starting_optimization_step: None
• finishing_optimization_step: 20,000
• num_train_dataset_workers: 32
• num_hosts: 8
• total_num_training_examples: 20,480,000
• steps_per_epoch: To be computed after first epoch
• num_beams: 5
• dropout: True
• dropout_probability: 0.1

Training results

step	eval_loss	train_loss	eval_wer	eval_cer
0	1.3582	7.9231	169.1230	127.5435
1000	0.9203	0.9748	24.0256	9.2618

Framework versions

• Transformers 4.29.0.dev0
• Datasets 2.12.0
• Tokenizers 0.13.3