Downloads · 30 days
17
2% of all-time downloads
wav2vec2-xlsr-georgian
sammy786/wav2vec2-xlsr-georgian
wav2vec2-xlsr-georgian is a automatic speech recognition model from sammy786. Use it when you need speech turned into text. It is set up for transformers. The card lists the license as apache-2.0.
This model is a fine-tuned version of facebook/wav2vec2-xls-r-1b on the MOZILLA-FOUNDATION/COMMONVOICE80 - ka dataset. It achieves the following results on evaluation set (which is 10 percent of train data set merged…
All-time downloads
726
Public
Repo size
7.7 GB
Likes
1
Public
Repo makeup
Click a slice to open those files.
.bin3.9 GB · 100%
At a glance
- Task
- Automatic Speech Recognition
- Library
- transformers
- License
- apache-2.0
- Model type
- wav2vec2
- Access
- Public
- Created
- Mar 2, 2022
- Updated
- Mar 24, 2022
- SHA
- 60c82690
Model card
From the Hugging Face model README
sammy786/wav2vec2-xlsr-georgian
This model is a fine-tuned version of facebook/wav2vec2-xls-r-1b on the MOZILLA-FOUNDATION/COMMON_VOICE_8_0 - ka dataset. It achieves the following results on evaluation set (which is 10 percent of train data set merged with other and dev datasets):
- Loss: 10.54
- Wer: 27.53
Model description
"facebook/wav2vec2-xls-r-1b" was finetuned.
Intended uses & limitations
More information needed
Training and evaluation data
Training data - Common voice Finnish train.tsv, dev.tsv and other.tsv
Training procedure
For creating the train dataset, all possible datasets were appended and 90-10 split was used.
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.000045637994662983496
- train_batch_size: 8
- eval_batch_size: 16
- seed: 13
- gradient_accumulation_steps: 4
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine_with_restarts
- lr_scheduler_warmup_steps: 500
- num_epochs: 30
- mixed_precision_training: Native AMP
Training results
| Step | Training Loss | Validation Loss | Wer |
|---|---|---|---|
| 200 | 4.152100 | 0.823672 | 0.967814 |
| 400 | 0.889500 | 0.196740 | 0.444792 |
| 600 | 0.493700 | 0.155659 | 0.366115 |
| 800 | 0.328000 | 0.138066 | 0.358069 |
| 1000 | 0.260600 | 0.119236 | 0.324989 |
| 1200 | 0.217200 | 0.114050 | 0.313366 |
| 1400 | 0.188800 | 0.112600 | 0.302190 |
| 1600 | 0.166900 | 0.111154 | 0.295485 |
| 1800 | 0.155500 | 0.109963 | 0.286544 |
| 2000 | 0.140400 | 0.107587 | 0.277604 |
| 2200 | 0.142600 | 0.105662 | 0.277157 |
| 2400 | 0.135400 | 0.105414 | 0.275369 |
Framework versions
- Transformers 4.16.0.dev0
- Pytorch 1.10.0+cu102
- Datasets 1.17.1.dev0
- Tokenizers 0.10.3
Evaluation Commands
- To evaluate on
mozilla-foundation/common_voice_8_0with splittest
python eval.py --model_id sammy786/wav2vec2-xlsr-georgian --dataset mozilla-foundation/common_voice_8_0 --config ka --split test
- Task
- Automatic Speech Recognition
- Library
- transformers
- Type
- wav2vec2
- License
- apache-2.0
- Languages
- ka
- Created
- Mar 2, 2022
- Updated
- Mar 24, 2022