metadata
license: apache-2.0
base_model: openai/whisper-medium
tags:
- generated_from_trainer
datasets:
- common_voice_13_0
metrics:
- wer
model-index:
- name: openai/whisper-medium
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: common_voice_13_0
type: common_voice_13_0
config: gl
split: test
args: gl
metrics:
- name: Wer
type: wer
value: 7.124379139072848
openai/whisper-medium
This model is a fine-tuned version of openai/whisper-medium on the common_voice_13_0 dataset. It achieves the following results on the evaluation set:
- Loss: 0.3218
- Wer: 7.1244
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: 64
- eval_batch_size: 32
- 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: 10000
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.0124 | 4.02 | 1000 | 0.2194 | 7.5383 |
| 0.0027 | 9.02 | 2000 | 0.2400 | 7.3382 |
| 0.0019 | 14.02 | 3000 | 0.2426 | 7.4055 |
| 0.0011 | 19.02 | 4000 | 0.2689 | 7.3520 |
| 0.0014 | 24.02 | 5000 | 0.2849 | 7.5314 |
| 0.0004 | 29.02 | 6000 | 0.2932 | 7.2589 |
| 0.0001 | 34.02 | 7000 | 0.3069 | 7.1485 |
| 0.0001 | 39.02 | 8000 | 0.3143 | 7.1485 |
| 0.0001 | 44.02 | 9000 | 0.3196 | 7.1227 |
| 0.0001 | 49.02 | 10000 | 0.3218 | 7.1244 |
Framework versions
- Transformers 4.33.0.dev0
- Pytorch 2.0.1+cu117
- Datasets 2.14.4
- Tokenizers 0.13.3