metadata
license: mit
base_model: facebook/w2v-bert-2.0
tags:
- generated_from_trainer
datasets:
- common_voice_16_0
metrics:
- wer
model-index:
- name: w2v-bert-2.0-hindi-colab-CV16.0
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: common_voice_16_0
type: common_voice_16_0
config: hi
split: test
args: hi
metrics:
- name: Wer
type: wer
value: 0.19428906708390378
w2v-bert-2.0-hindi-colab-CV16.0
This model is a fine-tuned version of facebook/w2v-bert-2.0 on the common_voice_16_0 dataset. It achieves the following results on the evaluation set:
- Loss: 0.3986
- Wer: 0.1943
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: 16
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 32
- 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 |
|---|---|---|---|---|
| 4.1542 | 1.35 | 300 | 0.8095 | 0.5287 |
| 0.3259 | 2.71 | 600 | 0.4394 | 0.3296 |
| 0.182 | 4.06 | 900 | 0.3599 | 0.2411 |
| 0.0988 | 5.42 | 1200 | 0.3444 | 0.2149 |
| 0.0617 | 6.77 | 1500 | 0.3469 | 0.2018 |
| 0.0312 | 8.13 | 1800 | 0.3702 | 0.1937 |
| 0.0137 | 9.48 | 2100 | 0.3986 | 0.1943 |
Framework versions
- Transformers 4.37.0.dev0
- Pytorch 2.1.2+cu121
- Datasets 2.16.1
- Tokenizers 0.15.0