Downloads · 30 days
6
1% of all-time downloads
wav2vec2-large-xls-r-300m-as
reichenbach/wav2vec2-large-xls-r-300m-as
wav2vec2-large-xls-r-300m-as is a automatic speech recognition model from reichenbach. 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
441
Public
Repo size
25.2 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin1.3 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
- 9ac11d0b
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. -->
wav2vec2-large-xls-r-300m-as
This model is a fine-tuned version of facebook/wav2vec2-xls-r-300m on the common_voice dataset. It achieves the following results on the evaluation set:
- Loss: 0.8318
- Wer: 0.5174
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: 0.0003
- 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_ratio: 0.12
- num_epochs: 120
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 4.882 | 25.0 | 400 | 1.2290 | 0.8182 |
| 0.8275 | 50.0 | 800 | 0.6835 | 0.5398 |
| 0.337 | 75.0 | 1200 | 0.7789 | 0.5107 |
| 0.2113 | 100.0 | 1600 | 0.8318 | 0.5174 |
Framework versions
- Transformers 4.16.2
- Pytorch 1.10.1+cu102
- Datasets 1.17.1.dev0
- Tokenizers 0.10.3
Test Evaluation
Common Voice Assamese Test Set (v7.0)
- WER: 0.7224
- CER: 0.2882
- Task
- Automatic Speech Recognition
- Library
- transformers
- Type
- wav2vec2
- License
- apache-2.0
- Languages
- as
- Created
- Mar 2, 2022
- Updated
- Mar 24, 2022