Downloads · 30 days
3
1% of all-time downloads
speech_representations_asr
federicocosta1989/speech_representations_asr
speech_representations_asr is a automatic speech recognition model from federicocosta1989. Use it when you need speech turned into text. It is set up for transformers.
should probably proofread and complete it, then remove this comment. --
All-time downloads
261
Public
Parameters
94.4M
755 MB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors378 MB · 100%
At a glance
- Task
- Automatic Speech Recognition
- Library
- transformers
- Model type
- hubert
- Access
- Public
- Created
- May 26, 2024
- Updated
- Nov 25, 2024
- SHA
- dde47cab
Base models
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. -->
speech_representations_asr
This model is a fine-tuned version of federicocosta1989/hubert_ca on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 3.7772
- Wer: 1.0
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: 16
- eval_batch_size: 8
- seed: 42
- 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: 5
- num_epochs: 20
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 16.8356 | 5.0 | 10 | 12.1508 | 1.0 |
| 6.3514 | 10.0 | 20 | 5.3859 | 1.0 |
| 4.0009 | 15.0 | 30 | 4.0669 | 1.0 |
| 4.36 | 20.0 | 40 | 3.7772 | 1.0 |
Framework versions
- Transformers 4.46.2
- Pytorch 2.5.1+cu121
- Datasets 3.1.0
- Tokenizers 0.20.3
- Task
- Automatic Speech Recognition
- Library
- transformers
- Type
- hubert
- Created
- May 26, 2024
- Updated
- Nov 25, 2024