|
|
--- |
|
|
library_name: transformers |
|
|
language: |
|
|
- en |
|
|
license: apache-2.0 |
|
|
base_model: openai/whisper-medium.en |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
datasets: |
|
|
- mozilla-foundation/common_voice_17_0 |
|
|
metrics: |
|
|
- wer |
|
|
model-index: |
|
|
- name: whisper-medium-en-cv-4.3 |
|
|
results: |
|
|
- task: |
|
|
name: Automatic Speech Recognition |
|
|
type: automatic-speech-recognition |
|
|
dataset: |
|
|
name: Common Voice 17.0 |
|
|
type: mozilla-foundation/common_voice_17_0 |
|
|
config: en |
|
|
split: test |
|
|
args: 'config: en, split: test' |
|
|
metrics: |
|
|
- name: Wer |
|
|
type: wer |
|
|
value: 12.705667276051189 |
|
|
--- |
|
|
|
|
|
<!-- 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-medium-en-cv-4.3 |
|
|
|
|
|
This model is a fine-tuned version of [openai/whisper-medium.en](https://huggingface.co/openai/whisper-medium.en) on the Common Voice 17.0 dataset. |
|
|
It achieves the following results on the evaluation set: |
|
|
- Loss: 0.3904 |
|
|
- Wer: 12.7057 |
|
|
|
|
|
## 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: 1.1e-05 |
|
|
- train_batch_size: 32 |
|
|
- eval_batch_size: 4 |
|
|
- seed: 42 |
|
|
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments |
|
|
- lr_scheduler_type: linear |
|
|
- lr_scheduler_warmup_steps: 150 |
|
|
- training_steps: 1125 |
|
|
- mixed_precision_training: Native AMP |
|
|
|
|
|
### Training results |
|
|
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Wer | |
|
|
|:-------------:|:------:|:----:|:---------------:|:-------:| |
|
|
| 0.299 | 0.3333 | 375 | 0.4141 | 13.8026 | |
|
|
| 0.261 | 0.6667 | 750 | 0.3941 | 13.5283 | |
|
|
| 0.2152 | 1.0 | 1125 | 0.3904 | 12.7057 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.51.3 |
|
|
- Pytorch 2.6.0+cu124 |
|
|
- Datasets 3.5.1 |
|
|
- Tokenizers 0.21.1 |
|
|
|
