81 lines
1.9 KiB
Markdown
81 lines
1.9 KiB
Markdown
|
---
|
||
|
|
language:
|
||
|
|
- tr
|
||
|
|
license: apache-2.0
|
||
|
|
base_model: openai/whisper-large-v3
|
||
|
|
tags:
|
||
|
|
- generated_from_trainer
|
||
|
|
datasets:
|
||
|
|
- mozilla-foundation/common_voice_17_0
|
||
|
|
metrics:
|
||
|
|
- wer
|
||
|
|
model-index:
|
||
|
|
- name: "Whisper Test TR - Erdi YAL\xC7IN"
|
||
|
|
results:
|
||
|
|
- task:
|
||
|
|
name: Automatic Speech Recognition
|
||
|
|
type: automatic-speech-recognition
|
||
|
|
dataset:
|
||
|
|
name: Common Voice 17.0
|
||
|
|
type: mozilla-foundation/common_voice_17_0
|
||
|
|
config: tr
|
||
|
|
split: None
|
||
|
|
args: 'config: tr, split: test'
|
||
|
|
metrics:
|
||
|
|
- name: Wer
|
||
|
|
type: wer
|
||
|
|
value: 12.795575896262395
|
||
|
|
---
|
||
|
|
|
||
|
|
<!-- 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 Test TR - Erdi YALÇIN
|
||
|
|
|
||
|
|
This model is a fine-tuned version of [openai/whisper-large-v3](https://huggingface.co/openai/whisper-large-v3) on the Common Voice 17.0 dataset.
|
||
|
|
It achieves the following results on the evaluation set:
|
||
|
|
- Loss: 0.1566
|
||
|
|
- Wer: 12.7956
|
||
|
|
|
||
|
|
## 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: 250
|
||
|
|
- training_steps: 1000
|
||
|
|
- mixed_precision_training: Native AMP
|
||
|
|
|
||
|
|
### Training results
|
||
|
|
|
||
|
|
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
||
|
|
|:-------------:|:-----:|:----:|:---------------:|:-------:|
|
||
|
|
| 0.1305 | 0.8 | 500 | 0.1764 | 14.6644 |
|
||
|
|
| 0.0496 | 1.6 | 1000 | 0.1566 | 12.7956 |
|
||
|
|
|
||
|
|
|
||
|
|
### Framework versions
|
||
|
|
|
||
|
|
- Transformers 4.40.1
|
||
|
|
- Pytorch 2.2.1+cu121
|
||
|
|
- Datasets 2.19.0
|
||
|
|
- Tokenizers 0.19.1
|