mr-small-whisper-oi / README.md
simran14's picture
End of training
0076569 verified
|
raw
history blame
1.93 kB
---
language:
- mr
license: apache-2.0
base_model: simran14/mr-whisper-small-retrained
tags:
- generated_from_trainer
datasets:
- mozilla-foundation/common_voice_11_0
metrics:
- wer
model-index:
- name: simrank14 Whisper Small marathi other+inval
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: Common Voice 11.0
type: mozilla-foundation/common_voice_11_0
config: mr
split: test
args: mr
metrics:
- name: Wer
type: wer
value: 13.910786387233223
---
<!-- 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. -->
# simrank14 Whisper Small marathi other+inval
This model is a fine-tuned version of [simran14/mr-whisper-small-retrained](https://huggingface.co/simran14/mr-whisper-small-retrained) on the Common Voice 11.0 dataset.
It achieves the following results on the evaluation set:
- Loss: 0.2512
- Wer: 13.9108
## 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
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 100
- training_steps: 3000
- mixed_precision_training: Native AMP
### Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|:-------------:|:------:|:----:|:---------------:|:-------:|
| 0.0181 | 4.7468 | 3000 | 0.2512 | 13.9108 |
### Framework versions
- Transformers 4.43.0.dev0
- Pytorch 2.3.0+cu121
- Datasets 2.20.1.dev0
- Tokenizers 0.19.1