whisper-small-hi / README.md
parasjain386's picture
End of training
0592c8f verified
|
raw
history blame
1.97 kB
---
language:
- hi
license: apache-2.0
base_model: openai/whisper-small
tags:
- generated_from_trainer
datasets:
- mozilla-foundation/common_voice_11_0
metrics:
- wer
model-index:
- name: Whisper Tiny Hi - Paras
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: Common Voice 11.0
type: mozilla-foundation/common_voice_11_0
config: hi
split: None
args: 'config: hi, split: test'
metrics:
- name: Wer
type: wer
value: 56.70447811732837
---
<!-- 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 Tiny Hi - Paras
This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the Common Voice 11.0 dataset.
It achieves the following results on the evaluation set:
- Loss: 0.5378
- Wer: 56.7045
## 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: 500
- training_steps: 3000
- mixed_precision_training: Native AMP
### Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|:-------------:|:------:|:----:|:---------------:|:-------:|
| 0.3147 | 2.4450 | 1000 | 0.5462 | 61.2969 |
| 0.1993 | 4.8900 | 2000 | 0.5212 | 57.2082 |
| 0.1321 | 7.3350 | 3000 | 0.5378 | 56.7045 |
### Framework versions
- Transformers 4.41.2
- Pytorch 1.12.1
- Datasets 2.20.0
- Tokenizers 0.19.1