# pip install -U transformers accelerate
# Load model directly
from transformers import AutoProcessor, AutoModelForCTC
processor = AutoProcessor.from_pretrained("Umong/w2v-bert-2.0-bd-regional-dialects")
model = AutoModelForCTC.from_pretrained("Umong/w2v-bert-2.0-bd-regional-dialects", device_map="auto")Quick Links
w2v-bert-2.0-bd-regional-dialects
This model is a fine-tuned version of facebook/w2v-bert-2.0 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.3110
- Wer: 0.6384
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: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 8
- 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: 6
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 3.7609 | 1.0 | 337 | 1.9209 | 0.9031 |
| 1.6809 | 2.0 | 674 | 1.5321 | 0.7254 |
| 1.4117 | 3.0 | 1011 | 1.3962 | 0.6925 |
| 1.2426 | 4.0 | 1348 | 1.3486 | 0.6724 |
| 1.0975 | 5.0 | 1685 | 1.3520 | 0.6524 |
| 0.9929 | 6.0 | 2022 | 1.3110 | 0.6384 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.1.2
- Datasets 2.16.0
- Tokenizers 0.15.2
- Downloads last month
- 22
Model tree for Umong/w2v-bert-2.0-bd-regional-dialects
Base model
facebook/w2v-bert-2.0
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="Umong/w2v-bert-2.0-bd-regional-dialects")