Automatic Speech Recognition
Transformers
PyTorch
Safetensors
Urdu
wav2vec2
mozilla-foundation/common_voice_7_0
Generated from Trainer
sv
robust-speech-event
model_for_talk
hf-asr-leaderboard
Instructions to use Maniac/wav2vec2-xls-r-urdu with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Maniac/wav2vec2-xls-r-urdu with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="Maniac/wav2vec2-xls-r-urdu")# Load model directly from transformers import AutoProcessor, AutoModelForCTC processor = AutoProcessor.from_pretrained("Maniac/wav2vec2-xls-r-urdu") model = AutoModelForCTC.from_pretrained("Maniac/wav2vec2-xls-r-urdu") - Notebooks
- Google Colab
- Kaggle
YAML Metadata Error:"model-index[0].name" is not allowed to be empty
This model is a fine-tuned version of facebook/wav2vec2-large-xlsr-53 on the MOZILLA-FOUNDATION/COMMON_VOICE_7_0 - UR dataset. It achieves the following results on the evaluation set:
- Loss: 1.5614
- Wer: 0.6765
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
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- training_steps: 1000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 1.9115 | 20.83 | 500 | 1.5400 | 0.7280 |
| 0.1155 | 41.67 | 1000 | 1.5614 | 0.6765 |
Framework versions
- Transformers 4.16.0.dev0
- Pytorch 1.10.1+cu102
- Datasets 1.17.1.dev0
- Tokenizers 0.11.0
- Downloads last month
- 9