# Load model directly
from transformers import AutoProcessor, AutoModelForCTC
processor = AutoProcessor.from_pretrained("amit0814/wav2vec2-large-xls-r-300m-hi-spot-colab")
model = AutoModelForCTC.from_pretrained("amit0814/wav2vec2-large-xls-r-300m-hi-spot-colab", device_map="auto")Quick Links
wav2vec2-large-xls-r-300m-hi-spot-colab
This model is a fine-tuned version of facebook/wav2vec2-xls-r-300m on the common_voice dataset.
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: 30
Training results
Framework versions
- Transformers 4.31.0
- Pytorch 2.0.1+cu118
- Datasets 1.18.3
- Tokenizers 0.13.3
- Downloads last month
- 2
Model tree for amit0814/wav2vec2-large-xls-r-300m-hi-spot-colab
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="amit0814/wav2vec2-large-xls-r-300m-hi-spot-colab")