Hugging Face's logo

yesj1234
/
en_xlsr_100p_run1

Automatic Speech Recognition
Transformers
Safetensors
wav2vec2
./train_dataset.py
Generated from Trainer
Inference Endpoints
Model card Files Community
en_xlsr_100p_run1 / README.md
yesj1234's picture
yesj1234
Upload folder using huggingface_hub
b84724e
preview code
|
raw
history blame contribute delete
1.34 kB
metadata
license: apache-2.0
base_model: facebook/wav2vec2-large-xlsr-53
tags:
  - automatic-speech-recognition
  - ./train_dataset.py
  - generated_from_trainer
model-index:
  - name: en_xlsr_100p_run1
    results: []

en_xlsr_100p_run1

This model is a fine-tuned version of facebook/wav2vec2-large-xlsr-53 on the ./TRAIN_DATASET.PY - NA 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: 2
  • eval_batch_size: 8
  • seed: 42
  • distributed_type: multi-GPU
  • num_devices: 4
  • gradient_accumulation_steps: 2
  • total_train_batch_size: 16
  • total_eval_batch_size: 32
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_steps: 2000
  • num_epochs: 10

Training results

Framework versions

  • Transformers 4.35.0
  • Pytorch 2.1.0+cu121
  • Datasets 2.14.6
  • Tokenizers 0.14.1