alakxender's picture
End of training
5ecb31a verified
|
raw
history blame
2.01 kB
---
language:
- dv
base_model: alakxender/w2v-bert-2.0-dhivehi-cv
tags:
- generated_from_trainer
datasets:
- mozilla-foundation/common_voice_17_0
metrics:
- wer
model-index:
- name: W2V2 Bert 2.0 Dv - alakxender
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: Common Voice 17.0
type: mozilla-foundation/common_voice_17_0
config: dv
split: test
args: 'config: dv, split: test'
metrics:
- name: Wer
type: wer
value: 0.45908364040881594
---
<!-- 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. -->
# W2V2 Bert 2.0 Dv - alakxender
This model is a fine-tuned version of [alakxender/w2v-bert-2.0-dhivehi-cv](https://huggingface.co/alakxender/w2v-bert-2.0-dhivehi-cv) on the Common Voice 17.0 dataset.
It achieves the following results on the evaluation set:
- Loss: 0.3580
- Wer: 0.4591
## 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: 5e-05
- train_batch_size: 32
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- 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: 500
- num_epochs: 10
- mixed_precision_training: Native AMP
### Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|:-------------:|:------:|:----:|:---------------:|:------:|
| 1.9272 | 3.8961 | 300 | 0.3712 | 0.5096 |
| 0.1846 | 7.7922 | 600 | 0.3580 | 0.4591 |
### Framework versions
- Transformers 4.41.0.dev0
- Pytorch 2.3.0+cu121
- Datasets 2.19.0
- Tokenizers 0.19.1