Downloads · 30 days
19
16% of all-time downloads
uaspeech-large-finetune-shorter-evals-29-11-8AM
neuronbit/uaspeech-large-finetune-shorter-evals-29-11-8AM
uaspeech-large-finetune-shorter-evals-29-11-8AM is a automatic speech recognition model from neuronbit. 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
116
Public
Parameters
1.5B
92.6 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors6.2 GB · 100%
At a glance
- Task
- Automatic Speech Recognition
- Library
- transformers
- License
- apache-2.0
- Model type
- whisper
- Access
- Public
- Created
- Nov 29, 2024
- Updated
- Nov 29, 2024
- SHA
- 0f0ea1f1
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. -->
uaspeech-large-finetune-shorter-evals-29-11-8AM
This model is a fine-tuned version of openai/whisper-large-v3 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.2763
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: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 100
- training_steps: 1500
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.3168 | 0.0828 | 200 | 0.3934 |
| 0.2478 | 0.1242 | 300 | 0.3321 |
| 0.2151 | 0.1656 | 400 | 0.3295 |
| 0.1683 | 0.2070 | 500 | 0.3064 |
| 0.1469 | 0.2483 | 600 | 0.3344 |
| 0.1183 | 0.2897 | 700 | 0.2818 |
| 0.0982 | 0.3311 | 800 | 0.2951 |
| 0.1028 | 0.3725 | 900 | 0.2737 |
| 0.0901 | 0.4139 | 1000 | 0.2723 |
| 0.0724 | 0.4553 | 1100 | 0.2761 |
| 0.0668 | 0.4967 | 1200 | 0.2807 |
| 0.0641 | 0.5381 | 1300 | 0.2699 |
| 0.041 | 0.5795 | 1400 | 0.2727 |
| 0.0438 | 0.6209 | 1500 | 0.2763 |
Framework versions
- Transformers 4.45.2
- Pytorch 2.5.1+cu124
- Datasets 3.1.0
- Tokenizers 0.20.3
- Task
- Automatic Speech Recognition
- Library
- transformers
- Type
- whisper
- License
- apache-2.0
- Created
- Nov 29, 2024
- Updated
- Nov 29, 2024