|
--- |
|
language: |
|
- 'no' |
|
license: apache-2.0 |
|
base_model: NbAiLab/nb-whisper-medium-RC1 |
|
tags: |
|
- audio |
|
- asr |
|
- automatic-speech-recognition |
|
- hf-asr-leaderboard |
|
model-index: |
|
- name: nb-whisper-medium-v0.8-vad3 |
|
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. --> |
|
|
|
# nb-whisper-medium-v0.8-vad3 |
|
|
|
This model is a fine-tuned version of [NbAiLab/nb-whisper-medium-RC1](https://huggingface.co./NbAiLab/nb-whisper-medium-RC1) on the NbAiLab/ncc_speech_styling_v2_vad3 dataset. |
|
It achieves the following results on the evaluation set: |
|
- step: 49999 |
|
- validation_nst_loss: 0.4365 |
|
- train_loss: 0.4233 |
|
- validation_nst_wer: 2.4062 |
|
- validation_nst_cer: 0.7262 |
|
- validation_nst_exact_wer: 3.0867 |
|
- validation_nst_exact_cer: 0.8297 |
|
- validation_clean_stortinget_no_loss: 0.7815 |
|
- validation_clean_stortinget_no_wer: 9.0005 |
|
- validation_clean_stortinget_no_cer: 5.7907 |
|
- validation_clean_stortinget_no_exact_wer: 12.1101 |
|
- validation_clean_stortinget_no_exact_cer: 6.2732 |
|
|
|
## 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: 50,000 |
|
- starting_optimization_step: None |
|
- finishing_optimization_step: 50,000 |
|
- num_train_dataset_workers: 32 |
|
- num_hosts: 8 |
|
- total_num_training_examples: 51,200,000 |
|
- steps_per_epoch: 7455 |
|
- 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 | 0.4223 | 0.8343 | 2.3463 | 0.7206 | 2.9397 | 0.8105 | 0.6313 | 8.8868 | 5.7697 | 11.8752 | 6.2280 | |
|
| 5000 | 0.4364 | 0.5289 | 2.6077 | 0.8063 | 3.2555 | 0.9057 | 0.6300 | 9.1071 | 5.8300 | 12.0840 | 6.3028 | |
|
| 10000 | 0.4353 | 0.4901 | 2.4824 | 0.7765 | 3.0867 | 0.8709 | 0.6463 | 9.2563 | 5.9382 | 12.2144 | 6.4042 | |
|
| 15000 | 0.4338 | 0.4760 | 2.4062 | 0.7290 | 3.0541 | 0.8324 | 0.6788 | 9.0052 | 5.7931 | 12.0816 | 6.2720 | |
|
| 20000 | 0.4343 | 0.4553 | 2.5695 | 0.7868 | 3.1956 | 0.8819 | 0.7058 | 9.1710 | 5.9434 | 12.2168 | 6.4280 | |
|
| 25000 | 0.4399 | 0.4476 | 2.4171 | 0.7439 | 3.0486 | 0.8398 | 0.7342 | 9.2800 | 5.9227 | 12.3947 | 6.4081 | |
|
| 30000 | 0.4356 | 0.4395 | 2.4008 | 0.7327 | 3.0377 | 0.8288 | 0.7352 | 9.2279 | 5.9985 | 12.2975 | 6.4826 | |
|
| 35000 | 0.4365 | 0.4371 | 2.5587 | 0.7756 | 3.2174 | 0.8764 | 0.7505 | 9.1852 | 5.8557 | 12.2714 | 6.3383 | |
|
| 40000 | 0.4358 | 0.4271 | 2.4607 | 0.7374 | 3.1248 | 0.8389 | 0.7643 | 9.1118 | 5.8569 | 12.2334 | 6.3449 | |
|
| 45000 | 0.4360 | 0.4211 | 2.5042 | 0.7458 | 3.0867 | 0.8334 | 0.7833 | 9.1094 | 5.8625 | 12.1646 | 6.3383 | |
|
| 49999 | 0.4365 | 0.4233 | 2.4062 | 0.7262 | 3.0867 | 0.8297 | |
|
| 49999 | 0.7815 | 0.4233 | 9.0005 | 5.7907 | 12.1101 | 6.2732 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.34.1 |
|
- Datasets 2.16.1 |
|
- Tokenizers 0.14.1 |
|
|
