Downloads · 30 days
4
2% of all-time downloads
whisper-medium-mix-it
deepdml/whisper-medium-mix-it
whisper-medium-mix-it is a automatic speech recognition model from deepdml. Use it when you need speech turned into text. The card lists the license as apache-2.0.
should probably proofread and complete it, then remove this comment. --
All-time downloads
212
Public
Parameters
764M
15.3 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors3.1 GB · 100%
At a glance
- Task
- Automatic Speech Recognition
- License
- apache-2.0
- Model type
- whisper
- Access
- Public
- Created
- Sep 30, 2024
- Updated
- Nov 17, 2024
- SHA
- 739bbf30
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. -->
Whisper Medium Mixed-Italian
This model is a fine-tuned version of openai/whisper-medium on the it datasets:
- mozilla-foundation/common_voice_17_0
- google/fleurs
- facebook/multilingual_librispeech
- facebook/voxpopuli
It achieves the following results on the evaluation set:
- Loss: 0.1318
- Wer: 6.8401
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: 32
- 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: 500
- training_steps: 5000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.1502 | 0.2 | 1000 | 0.1708 | 9.0922 |
| 0.1584 | 0.4 | 2000 | 0.1554 | 8.1757 |
| 0.1309 | 0.6 | 3000 | 0.1426 | 7.4142 |
| 0.0984 | 0.8 | 4000 | 0.1370 | 7.1298 |
| 0.0933 | 1.0 | 5000 | 0.1318 | 6.8401 |
Framework versions
- Transformers 4.42.0.dev0
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1
- Task
- Automatic Speech Recognition
- Type
- whisper
- License
- apache-2.0
- Languages
- it
- Created
- Sep 30, 2024
- Updated
- Nov 17, 2024