metadata

library_name: peft
language:
  - it
license: apache-2.0
base_model: openai/whisper-medium
tags:
  - generated_from_trainer
datasets:
  - ASR_Synthetic_Speecht5_TTS
metrics:
  - wer
model-index:
  - name: Whisper Medium
    results:
      - task:
          type: automatic-speech-recognition
          name: Automatic Speech Recognition
        dataset:
          name: ASR_Synthetic_Speecht5_TTS
          type: ASR_Synthetic_Speecht5_TTS
          config: default
          split: test
          args: default
        metrics:
          - type: wer
            value: 171.5307582260372
            name: Wer

Whisper Medium

This model is a fine-tuned version of openai/whisper-medium on the ASR_Synthetic_Speecht5_TTS dataset. It achieves the following results on the evaluation set:

Loss: 2.9413
Wer: 171.5308

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: 4
eval_batch_size: 4
seed: 42
gradient_accumulation_steps: 2
total_train_batch_size: 8
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 50
training_steps: 200
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
6.8678	0.0244	25	4.4434	154.2203
2.6877	0.0489	50	3.4026	144.0629
1.8792	0.0733	75	3.2962	77.3963
1.5587	0.0978	100	3.2969	78.9700
1.4194	0.1222	125	2.9920	75.1073
1.2356	0.1467	150	2.9471	184.2632
1.1741	0.1711	175	2.9542	189.4134
1.0451	0.1956	200	2.9413	171.5308

Framework versions

PEFT 0.13.2
Transformers 4.44.2
Pytorch 2.2.0
Datasets 3.1.0
Tokenizers 0.19.1