metadata
license: apache-2.0
base_model: openai/whisper-base
tags:
- generated_from_trainer
datasets:
- common_voice_11_0
metrics:
- wer
model-index:
- name: >-
whisper-base-cs-cv11-timestetch02-gain01-pitch02-gaussian02-lowpass01-timemask50-freqmask50
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: common_voice_11_0
type: common_voice_11_0
config: cs
split: None
args: cs
metrics:
- name: Wer
type: wer
value: 42.66401443990128
whisper-base-cs-cv11-timestetch02-gain01-pitch02-gaussian02-lowpass01-timemask50-freqmask50
This model is a fine-tuned version of openai/whisper-base on the common_voice_11_0 dataset. It achieves the following results on the evaluation set:
- Loss: 0.4240
- Wer: 42.6640
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: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 32
- 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 |
|---|---|---|---|---|
| 1.5795 | 0.72 | 1000 | 0.5715 | 52.0039 |
| 1.3147 | 1.44 | 2000 | 0.4734 | 46.0014 |
| 1.1304 | 2.17 | 3000 | 0.4346 | 43.5205 |
| 1.1056 | 2.89 | 4000 | 0.4240 | 42.6640 |
Framework versions
- Transformers 4.38.0
- Pytorch 2.2.0+cu121
- Datasets 2.17.1
- Tokenizers 0.15.2