metadata
language:
- as
license: apache-2.0
tags:
- whisper-event
- generated_from_trainer
datasets:
- mozilla-foundation/common_voice_11_0
metrics:
- wer
model-index:
- name: openai/whisper-small-Assamese
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: Common Voice 11.0
type: mozilla-foundation/common_voice_11_0
config: as
split: test
args: as
metrics:
- name: Wer
type: wer
value: 32.01588160981772
openai/whisper-small-Assamese
This model is a fine-tuned version of kpriyanshu256/whisper-small-as-500-64-1e-05-bn on the Common Voice 11.0 dataset. It achieves the following results on the evaluation set:
- Loss: 0.5071
- Wer: 32.0159
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: 8
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 50
- training_steps: 500
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.0658 | 8.01 | 100 | 0.3295 | 31.9978 |
| 0.0027 | 16.02 | 200 | 0.4516 | 31.8896 |
| 0.0005 | 24.02 | 300 | 0.4881 | 31.9256 |
| 0.0003 | 33.01 | 400 | 0.5026 | 31.9437 |
| 0.0003 | 41.02 | 500 | 0.5071 | 32.0159 |
Framework versions
- Transformers 4.26.0.dev0
- Pytorch 1.11.0
- Datasets 2.1.0
- Tokenizers 0.12.1