|
--- |
|
library_name: transformers |
|
language: |
|
- en |
|
license: apache-2.0 |
|
base_model: openai/whisper-large |
|
tags: |
|
- generated_from_trainer |
|
datasets: |
|
- Jzuluaga/atcosim_corpus |
|
metrics: |
|
- wer |
|
model-index: |
|
- name: Whisper Large - Whisper with atcosim_corpus |
|
results: |
|
- task: |
|
name: Automatic Speech Recognition |
|
type: automatic-speech-recognition |
|
dataset: |
|
name: The ATCOSIM Air Traffic Control Simulation Speech corpus is a speech database |
|
of air traffic control (ATC) operator speech, provided by Graz University |
|
of Technology (TUG) and Eurocontrol Experimental Centre (EEC) |
|
type: Jzuluaga/atcosim_corpus |
|
args: 'config: en, split: test' |
|
metrics: |
|
- name: Wer |
|
type: wer |
|
value: 0.9495627594735447 |
|
--- |
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
# Whisper Large - Whisper with atcosim_corpus |
|
|
|
This model is a fine-tuned version of [openai/whisper-large](https://huggingface.co/openai/whisper-large) on the The ATCOSIM Air Traffic Control Simulation Speech corpus is a speech database of air traffic control (ATC) operator speech, provided by Graz University of Technology (TUG) and Eurocontrol Experimental Centre (EEC) dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.0413 |
|
- Wer: 0.9496 |
|
|
|
## 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: 1e-05 |
|
- train_batch_size: 16 |
|
- eval_batch_size: 8 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_steps: 500 |
|
- training_steps: 4000 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Wer | |
|
|:-------------:|:------:|:----:|:---------------:|:------:| |
|
| 0.012 | 2.0921 | 1000 | 0.0405 | 1.2543 | |
|
| 0.0019 | 4.1841 | 2000 | 0.0372 | 1.0776 | |
|
| 0.0001 | 6.2762 | 3000 | 0.0407 | 0.9716 | |
|
| 0.0 | 8.3682 | 4000 | 0.0413 | 0.9496 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.44.2 |
|
- Pytorch 2.4.0+cu121 |
|
- Datasets 2.21.0 |
|
- Tokenizers 0.19.1 |
|
|
