Downloads · 30 days
21
3% of all-time downloads
w2v-bert-2.0-mongolian-colab-CV16.0
ylacombe/w2v-bert-2.0-mongolian-colab-CV16.0
w2v-bert-2.0-mongolian-colab-CV16.0 is a automatic speech recognition model from ylacombe. Use it when you need speech turned into text. It is set up for transformers.
should probably proofread and complete it, then remove this comment. --
All-time downloads
793
Public
Parameters
606M
38.8 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors2.4 GB · 100%
At a glance
- Task
- Automatic Speech Recognition
- Library
- transformers
- Model type
- wav2vec2-bert
- Access
- Public
- Created
- Jan 18, 2024
- Updated
- Jan 24, 2024
- SHA
- 5b76dde3
Base models
Datasets
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. -->
w2v-bert-2.0-mongolian-colab-CV16.0
This model is a fine-tuned version of ylacombe/w2v-bert-2.0 on the common_voice_16_0 dataset. It achieves the following results on the evaluation set:
- Loss: 0.5279
- Wer: 0.3382
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: 5e-05
- train_batch_size: 16
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 2.0592 | 2.37 | 300 | 0.7052 | 0.5907 |
| 0.3893 | 4.74 | 600 | 0.5848 | 0.4508 |
| 0.1926 | 7.11 | 900 | 0.5277 | 0.3830 |
| 0.0857 | 9.49 | 1200 | 0.5279 | 0.3382 |
Framework versions
- Transformers 4.37.0.dev0
- Pytorch 2.1.0+cu121
- Datasets 2.16.1
- Tokenizers 0.15.1
- Task
- Automatic Speech Recognition
- Library
- transformers
- Type
- wav2vec2-bert
- Created
- Jan 18, 2024
- Updated
- Jan 24, 2024