Downloads · 30 days
6
10% of all-time downloads
whisper-small-phonemes
Minu1234/whisper-small-phonemes
whisper-small-phonemes is a automatic speech recognition model from Minu1234. 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
62
Public
Repo size
21.3 GB
Likes
1
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
- Oct 23, 2023
- Updated
- Oct 28, 2023
- SHA
- cf5e466f
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 Small En - Minu Kumari
This model is a fine-tuned version of openai/whisper-small on the Polly Generated Voice v0.1 dataset. It achieves the following results on the evaluation set:
- Loss: 0.6189
- Wer: 32.9596
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: 16
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 5
- training_steps: 100
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 3.3582 | 1.0 | 5 | 4.3222 | 100.4484 |
| 2.8958 | 2.0 | 10 | 2.6835 | 100.6726 |
| 1.679 | 3.0 | 15 | 1.8785 | 100.8969 |
| 1.0805 | 4.0 | 20 | 1.4200 | 98.4305 |
| 0.7281 | 5.0 | 25 | 1.1074 | 63.2287 |
| 0.4916 | 6.0 | 30 | 0.9027 | 66.5919 |
| 0.3474 | 7.0 | 35 | 0.7891 | 55.1570 |
| 0.2581 | 8.0 | 40 | 0.7255 | 65.9193 |
| 0.1996 | 9.0 | 45 | 0.6849 | 76.4574 |
| 0.1588 | 10.0 | 50 | 0.6598 | 69.0583 |
| 0.1295 | 11.0 | 55 | 0.6491 | 64.3498 |
| 0.1081 | 12.0 | 60 | 0.6377 | 54.4843 |
| 0.0933 | 13.0 | 65 | 0.6323 | 34.5291 |
| 0.0829 | 14.0 | 70 | 0.6280 | 34.9776 |
| 0.0749 | 15.0 | 75 | 0.6276 | 35.2018 |
| 0.0693 | 16.0 | 80 | 0.6264 | 33.8565 |
| 0.065 | 17.0 | 85 | 0.6225 | 34.3049 |
| 0.062 | 18.0 | 90 | 0.6207 | 33.6323 |
| 0.06 | 19.0 | 95 | 0.6198 | 33.4081 |
| 0.0585 | 20.0 | 100 | 0.6189 | 32.9596 |
Framework versions
- Transformers 4.34.1
- Pytorch 2.1.0+cu118
- Datasets 2.14.5
- Tokenizers 0.14.1
- Task
- Automatic Speech Recognition
- Library
- transformers
- Type
- whisper
- License
- apache-2.0
- Languages
- en
- Created
- Oct 23, 2023
- Updated
- Oct 28, 2023