Downloads · 30 days
2
2% of all-time downloads
whisper-medium-cv17-es-5-steps_proc1
mmarron14/whisper-medium-cv17-es-5-steps_proc1
whisper-medium-cv17-es-5-steps_proc1 is a automatic speech recognition model from mmarron14. Use it when you need speech turned into text. It is set up for transformers. The card lists the license as apache-2.0.
should probably proofread and complete it, then remove this comment. --
All-time downloads
118
Public
Parameters
764M
15.3 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors3.1 GB · 100%
At a glance
- Task
- Automatic Speech Recognition
- Library
- transformers
- License
- apache-2.0
- Model type
- whisper
- Access
- Public
- Created
- Oct 15, 2025
- Updated
- Dec 1, 2025
- SHA
- a43169e3
Base models
Datasets
Model card
From the Hugging Face model README
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
Whisper Medium CV17 Es 5 steps with processing of text using method 1; with same configuration as 5-steps-sin_proc: no filtering 30sec with customised optimizer- María Marrón
This model is a fine-tuned version of openai/whisper-medium on the Common Voice 17.0 dataset. It achieves the following results on the evaluation set:
- Loss: 0.1937
- Wer Ortho: 6.8883
- Wer: 375.5020
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: 1e-05
- train_batch_size: 2
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 32
- total_train_batch_size: 64
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- training_steps: 5
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer Ortho | Wer |
|---|---|---|---|---|---|
| No log | 0.2 | 1 | 3.3895 | 994.8653 | 63402.4096 |
| No log | 0.4 | 2 | 1.5156 | 976.2316 | 62252.6104 |
| No log | 0.6 | 3 | 0.6959 | 811.1335 | 51731.7269 |
| No log | 0.8 | 4 | 0.2952 | 39.6266 | 2471.8876 |
| No log | 1.0 | 5 | 0.1937 | 6.8883 | 375.5020 |
Framework versions
- Transformers 4.53.2
- Pytorch 2.9.1+cu128
- Datasets 2.14.4
- Tokenizers 0.21.4
- Task
- Automatic Speech Recognition
- Library
- transformers
- Type
- whisper
- License
- apache-2.0
- Languages
- es
- Created
- Oct 15, 2025
- Updated
- Dec 1, 2025