Downloads · 30 days
7
12% of all-time downloads
subh_whisper_small_distil_att_loss_mozilla_epochs_50_batch_8
rohitp1/subh_whisper_small_distil_att_loss_mozilla_epochs_50_batch_8
subh_whisper_small_distil_att_loss_mozilla_epochs_50_batch_8 is a automatic speech recognition model from rohitp1. 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
60
Public
Repo size
6.8 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin967 MB · 100%
At a glance
- Task
- Automatic Speech Recognition
- Library
- transformers
- License
- apache-2.0
- Model type
- whisper
- Access
- Public
- Created
- May 22, 2023
- Updated
- Jun 7, 2023
- SHA
- d5d12960
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. -->
subh_whisper_small_distil_att_loss_mozilla_epochs_50_batch_8
This model is a fine-tuned version of rohitp1/dgx1_whisper_small_finetune_teacher_babble_noise_mozilla_40_epochs_batch_8 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.5208
- Wer: 100.0
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: 8
- eval_batch_size: 1
- seed: 42
- gradient_accumulation_steps: 512
- total_train_batch_size: 4096
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.2
- num_epochs: 50
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 3.1278 | 4.39 | 150 | 0.4135 | 100.0 |
| 4.6475 | 8.78 | 300 | 0.4516 | 100.0 |
| 5.5834 | 13.17 | 450 | 0.4801 | 100.0 |
| 6.7365 | 17.55 | 600 | 0.4981 | 100.0 |
| 7.3081 | 21.94 | 750 | 0.5108 | 100.0 |
| 7.4849 | 26.33 | 900 | 0.5208 | 100.0 |
Framework versions
- Transformers 4.29.2
- Pytorch 1.12.1
- Datasets 2.8.0
- Tokenizers 0.13.2
- Task
- Automatic Speech Recognition
- Library
- transformers
- Type
- whisper
- License
- apache-2.0
- Created
- May 22, 2023
- Updated
- Jun 7, 2023