Hugging Face's logo

YMEA
/
whisper-pathe-bambara_V1

Automatic Speech Recognition
Transformers
Safetensors
Bambara
whisper
Generated from Trainer
Inference Endpoints
Model card Files Community
whisper-pathe-bambara_V1 / README.md
YMEA's picture
YMEA
End of training
02f8d04 verified
preview code
|
raw
history blame contribute delete
1.32 kB
metadata
library_name: transformers
language:
  - bam
license: apache-2.0
base_model: openai/whisper-medium
tags:
  - generated_from_trainer
datasets:
  - YMEA/audio_15k_v2
model-index:
  - name: audio
    results: []

audio

This model is a fine-tuned version of openai/whisper-medium on the Bambara TTS 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: 0.0001
  • train_batch_size: 1
  • eval_batch_size: 8
  • seed: 42
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 4
  • optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_steps: 250
  • num_epochs: 10
  • mixed_precision_training: Native AMP

Training results

Framework versions

  • Transformers 4.47.1
  • Pytorch 2.5.1+cu121
  • Datasets 3.2.0
  • Tokenizers 0.21.0