metadata
library_name: peft
license: apache-2.0
base_model: openai/whisper-large-v2
tags:
- generated_from_trainer
- multilingual
- ASR
- Open-Source
- african-language
- Songhoy
language:
- hsn
- fr
model-index:
- name: songhoy-asr-v1
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: songhoy-asr
type: custom
split: test
args:
language: hsn
metrics:
- name: Test WER
type: wer
value: 16.58
- name: Test CER
type: cer
value: 4.63
pipeline_tag: automatic-speech-recognition
songhoy-asr-v1-ic
This model is a fine-tuned version of openai/whisper-large-v2 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.1897
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: 0.001
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 32
- 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: 50
- num_epochs: 4
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss |
---|---|---|---|
0.3661 | 1.0 | 245 | 0.3118 |
0.2712 | 2.0 | 490 | 0.2215 |
0.2008 | 3.0 | 735 | 0.2011 |
0.1518 | 3.9857 | 976 | 0.1897 |
Framework versions
- PEFT 0.14.1.dev0
- Transformers 4.50.0.dev0
- Pytorch 2.5.1+cu124
- Datasets 3.2.0
- Tokenizers 0.21.0