Downloads · 30 days
18
2% of all-time downloads
wav2vec2-large-xls-r-300m-assamese
infinitejoy/wav2vec2-large-xls-r-300m-assamese
wav2vec2-large-xls-r-300m-assamese is a automatic speech recognition model from infinitejoy. 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-300m on the commonvoice70 dataset. It achieves the following results on the evaluation set:
All-time downloads
843
Public
Repo size
37.9 GB
Likes
1
Public
Repo makeup
Click a slice to open those files.
.bin3.1 GB · 99%
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
- 3e7f332d
Model card
From the Hugging Face model README
wav2vec2-large-xls-r-300m-assamese
This model is a fine-tuned version of facebook/wav2vec2-xls-r-300m on the common_voice_7_0 dataset. It achieves the following results on the evaluation set:
- WER: 0.7954545454545454
- CER: 0.32341269841269843
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
To compute the evaluation parameters
cd wav2vec2-large-xls-r-300m-assamese; python eval.py --model_id ./ --dataset mozilla-foundation/common_voice_7_0 --config as --split test --log_outputs
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 3e-4
- train_batch_size: 16
- eval_batch_size: 8
- seed: not given
- 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: 400
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 1.584065 | NA | 400 | 1.584065 | 0.915512 |
| 1.658865 | Na | 800 | 1.658865 | 0.805096 |
| 1.882352 | NA | 1200 | 1.882352 | 0.820742 |
| 1.881240 | NA | 1600 | 1.881240 | 0.810907 |
| 2.159748 | NA | 2000 | 2.159748 | 0.804202 |
| 1.992871 | NA | 2400 | 1.992871 | 0.803308 |
| 2.201436 | NA | 2800 | 2.201436 | 0.802861 |
| 2.165218 | NA | 3200 | 2.165218 | 0.793920 |
| 2.253643 | NA | 3600 | 2.253643 | 0.796603 |
| 2.265880 | NA | 4000 | 2.265880 | 0.790344 |
| 2.293935 | NA | 4400 | 2.293935 | 0.797050 |
| 2.288851 | NA | 4800 | 2.288851 | 0.784086 |
Framework versions
- Transformers 4.11.3
- Pytorch 1.10.0+cu113
- Datasets 1.13.3
- Tokenizers 0.10.3
- Task
- Automatic Speech Recognition
- Library
- transformers
- Type
- wav2vec2
- License
- apache-2.0
- Languages
- as
- Created
- Mar 2, 2022
- Updated
- Mar 24, 2022