Downloads · 30 days
187
5% of all-time downloads
whisper-large-v3-sr-cmb
Sagicc/whisper-large-v3-sr-cmb
whisper-large-v3-sr-cmb is a automatic speech recognition model from Sagicc. 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
4K
Public
Parameters
1.5B
6.2 GB on disk
Likes
4
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
- Dec 1, 2023
- Updated
- Dec 2, 2023
- SHA
- ee8c1d78
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 Large v3 cmb
This model is a fine-tuned version of openai/whisper-large-v3 on the Common Voice 13, Google Fleurs and juzne vesti dataset. It achieves the following results on the evaluation set:
- Loss: 0.1111
- Wer Ortho: 0.1339
- Wer: 0.0415
Model description
Dataset Juzne vesti is published by
Rupnik, Peter and Ljubešić, Nikola, 2022,
ASR training dataset for Serbian JuzneVesti-SR v1.0, Slovenian language resource repository CLARIN.SI, ISSN 2820-4042,
http://hdl.handle.net/11356/1679.
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: 2
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 8
- 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: 50
- training_steps: 1500
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer Ortho | Wer |
|---|---|---|---|---|---|
| 0.2766 | 0.48 | 500 | 0.1350 | 0.1670 | 0.0595 |
| 0.2813 | 0.95 | 1000 | 0.1134 | 0.1426 | 0.0491 |
| 0.1858 | 1.43 | 1500 | 0.1111 | 0.1339 | 0.0415 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.0.1+cu117
- Datasets 2.14.5
- Tokenizers 0.14.1
- Task
- Automatic Speech Recognition
- Library
- transformers
- Type
- whisper
- License
- apache-2.0
- Languages
- sr
- Created
- Dec 1, 2023
- Updated
- Dec 2, 2023