Downloads · 30 days
13
20% of all-time downloads
wav2vec2-large-mms-1b-korean-colab_v0
weekcircle/wav2vec2-large-mms-1b-korean-colab_v0
wav2vec2-large-mms-1b-korean-colab_v0 is a automatic speech recognition model from weekcircle. Use it when you need speech turned into text. It is set up for transformers. The card lists the license as cc-by-nc-4.0.
should probably proofread and complete it, then remove this comment. --
All-time downloads
64
Public
Repo size
38.7 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin3.9 GB · 100%
At a glance
- Task
- Automatic Speech Recognition
- Library
- transformers
- License
- cc-by-nc-4.0
- Model type
- wav2vec2
- Access
- Public
- Created
- Jul 17, 2023
- Updated
- Jul 17, 2023
- SHA
- fb9921e6
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. -->
wav2vec2-large-mms-1b-korean-colab_v0
This model is a fine-tuned version of facebook/mms-1b-l1107 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.7087
- Wer: 0.4815
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: 0.001
- train_batch_size: 8
- 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: 100
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 2.7116 | 0.18 | 100 | 2.4552 | 0.8749 |
| 2.2205 | 0.36 | 200 | 1.9366 | 0.8416 |
| 1.8449 | 0.53 | 300 | 1.6497 | 0.7798 |
| 1.6396 | 0.71 | 400 | 1.4163 | 0.6969 |
| 1.5395 | 0.89 | 500 | 1.2572 | 0.6723 |
| 1.3307 | 1.07 | 600 | 1.1234 | 0.6368 |
| 1.148 | 1.24 | 700 | 1.0645 | 0.6295 |
| 1.1263 | 1.42 | 800 | 0.9780 | 0.5975 |
| 1.0562 | 1.6 | 900 | 0.9087 | 0.5845 |
| 1.0059 | 1.78 | 1000 | 0.8727 | 0.5739 |
| 0.9731 | 1.95 | 1100 | 0.8289 | 0.5392 |
| 0.821 | 2.13 | 1200 | 0.7917 | 0.5270 |
| 0.7899 | 2.31 | 1300 | 0.7763 | 0.5183 |
| 0.7815 | 2.49 | 1400 | 0.7469 | 0.5080 |
| 0.7743 | 2.66 | 1500 | 0.7218 | 0.4945 |
| 0.7548 | 2.84 | 1600 | 0.7087 | 0.4815 |
Framework versions
- Transformers 4.31.0.dev0
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3
- Task
- Automatic Speech Recognition
- Library
- transformers
- Type
- wav2vec2
- License
- cc-by-nc-4.0
- Created
- Jul 17, 2023
- Updated
- Jul 17, 2023