|
--- |
|
language: |
|
- 'no' |
|
license: apache-2.0 |
|
tags: |
|
- audio |
|
- asr |
|
- automatic-speech-recognition |
|
- hf-asr-leaderboard |
|
model-index: |
|
- name: scream_small_beta |
|
results: [] |
|
--- |
|
|
|
<!-- This model card has been generated automatically according to the information Keras had access to. You should |
|
probably proofread and complete it, then remove this comment. --> |
|
|
|
# scream_small_beta |
|
|
|
This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the NbAiLab/ncc_speech 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: 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: 25,000 |
|
- starting_optimization_step: None |
|
- finishing_optimization_step: 25,000 |
|
- num_train_dataset_workers: 32 |
|
- num_hosts: 8 |
|
- total_num_training_examples: 25,600,000 |
|
- steps_per_epoch: _To be computed after first epoch_ |
|
- num_beams: None |
|
- dropout: True |
|
- bpe_dropout_probability: 0.1 |
|
|
|
### Training results |
|
|
|
| step | validation_fleurs_loss | train_loss | validation_fleurs_wer | validation_fleurs_cer | validation_fleurs_exact_wer | validation_fleurs_exact_cer | validation_stortinget_loss | validation_stortinget_wer | validation_stortinget_cer | validation_stortinget_exact_wer | validation_stortinget_exact_cer | validation_nrk_tv_loss | validation_nrk_tv_wer | validation_nrk_tv_cer | validation_nrk_tv_exact_wer | validation_nrk_tv_exact_cer | |
|
|:----:|:----------------------:|:----------:|:---------------------:|:---------------------:|:---------------------------:|:---------------------------:|:--------------------------:|:-------------------------:|:-------------------------:|:-------------------------------:|:-------------------------------:|:----------------------:|:---------------------:|:---------------------:|:---------------------------:|:---------------------------:| |
|
| 0 | 1.2013 | 2.7117 | 32.3914 | 9.8343 | 35.7228 | 10.9398 | 1.4988 | 44.0673 | 22.9444 | 48.2612 | 24.2595 | 1.8165 | 79.9390 | 54.6020 | 89.7612 | 56.8482 | |
|
| 1000 | 0.5796 | 1.0147 | 16.1214 | 5.2624 | 19.9821 | 6.2962 | 0.4822 | 22.0502 | 13.3652 | 25.7586 | 14.0827 | 1.0170 | 51.9187 | 37.4011 | 59.7853 | 39.0187 | |
|
| 2000 | 0.4483 | 0.8851 | 12.4628 | 4.6064 | 16.2485 | 5.6101 | 0.3988 | 18.2903 | 11.9625 | 21.9050 | 12.6098 | 0.9032 | 46.8241 | 34.8122 | 55.1298 | 36.2314 | |
|
| 3000 | 0.4130 | 0.8246 | 11.6002 | 4.7445 | 15.4122 | 5.7357 | 0.3602 | 16.9068 | 11.3683 | 20.4599 | 11.9897 | 0.8434 | 46.9972 | 35.4892 | 54.8885 | 36.8431 | |
|
| 4000 | 0.3946 | 0.7897 | 10.2617 | 4.2365 | 14.4564 | 5.1703 | 0.3359 | 16.1132 | 11.0146 | 19.5868 | 11.6112 | 0.8112 | 44.8580 | 33.8810 | 52.6086 | 35.2519 | |
|
| 5000 | 0.4532 | 0.7438 | 10.3807 | 4.2809 | 14.1876 | 5.2090 | 0.3295 | 15.7676 | 10.8729 | 19.2134 | 11.4603 | 0.8051 | 44.2068 | 33.3323 | 51.3438 | 34.6898 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.31.0.dev0 |
|
- Datasets 2.13.0 |
|
- Tokenizers 0.13.3 |
|
|
