Downloads · 30 days
23
5% of all-time downloads
odia_whisper_small_v3.0
Ranjit/odia_whisper_small_v3.0
odia_whisper_small_v3.0 is a automatic speech recognition model from Ranjit. Use it when you need speech turned into text. It is set up for transformers. The card lists the license as cc-by-nd-4.0.
should probably proofread and complete it, then remove this comment. --
All-time downloads
429
Public
Repo size
1.9 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
- cc-by-nd-4.0
- Model type
- whisper
- Access
- Public
- Created
- May 31, 2023
- Updated
- Jun 9, 2023
- SHA
- e8df31c3
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. -->
Ranjit/whisper_small_35k_or
This model is a fine-tuned version of openai/whisper-small on the mozilla-foundation/common_voice_11_0 and other dataset. It achieves the following results on the evaluation set:
- Loss: 0.2584
- Wer: 13.8614
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 1e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.98) and epsilon=1e-06
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 200
- training_steps: 5000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.0022 | 5.59 | 1000 | 0.2405 | 13.9995 |
| 0.0005 | 11.17 | 2000 | 0.2584 | 13.8614 |
| 0.0002 | 16.76 | 3000 | 0.2683 | 16.5598 |
| 0.0 | 22.35 | 4000 | 0.2907 | 15.0380 |
| 0.0 | 27.93 | 5000 | 0.3085 | 14.2035 |
- Task
- Automatic Speech Recognition
- Library
- transformers
- Type
- whisper
- License
- cc-by-nd-4.0
- Languages
- or
- Created
- May 31, 2023
- Updated
- Jun 9, 2023