# Load model directly
from transformers import AutoProcessor, AutoModelForCTC
processor = AutoProcessor.from_pretrained("menhior/wav2vec2-large-xls-r-300m-azeri-colab-test")
model = AutoModelForCTC.from_pretrained("menhior/wav2vec2-large-xls-r-300m-azeri-colab-test", device_map="auto")Quick Links
wav2vec2-large-xls-r-300m-azeri-colab-test
This model is a fine-tuned version of menhior/wav2vec2-large-xls-r-300m-turkish-colab-full on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.5444
- Wer: 0.2736
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: 0.0003
- 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: 20
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 3.9357 | 4.4 | 400 | 0.5790 | 0.4613 |
| 0.2762 | 8.79 | 800 | 0.4553 | 0.3248 |
| 0.0788 | 13.19 | 1200 | 0.5028 | 0.2809 |
| 0.0293 | 17.58 | 1600 | 0.5444 | 0.2736 |
Framework versions
- Transformers 4.34.0
- Pytorch 2.0.1+cu118
- Datasets 1.18.3
- Tokenizers 0.14.0
- Downloads last month
- 25
Model tree for menhior/wav2vec2-large-xls-r-300m-azeri-colab-test
Base model
facebook/wav2vec2-xls-r-300m
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="menhior/wav2vec2-large-xls-r-300m-azeri-colab-test")