Downloads · 30 days
8
2% of all-time downloads
wav2vec2-2-bart-large-cnn-no-adapter
sanchit-gandhi/wav2vec2-2-bart-large-cnn-no-adapter
wav2vec2-2-bart-large-cnn-no-adapter is a automatic speech recognition model from sanchit-gandhi. 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
363
Public
Repo size
27.4 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin2.3 GB · 69%
At a glance
- Task
- Automatic Speech Recognition
- Library
- transformers
- Model type
- speech-encoder-decoder
- Access
- Public
- Created
- Mar 26, 2022
- Updated
- Mar 28, 2022
- SHA
- a62d17b5
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. -->
This model was trained from scratch on the librispeech_asr dataset. It achieves the following results on the evaluation set:
- Loss: 3.9938
- Wer: 0.9745
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: 3e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 16
- total_train_batch_size: 128
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 10.0
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 4.9301 | 2.24 | 500 | 4.6291 | 0.9601 |
| 4.4562 | 4.48 | 1000 | 4.3604 | 0.9608 |
| 3.8356 | 6.73 | 1500 | 4.0728 | 0.9530 |
| 3.2716 | 8.97 | 2000 | 3.9938 | 0.9745 |
Framework versions
- Transformers 4.17.0.dev0
- Pytorch 1.10.2+cu113
- Datasets 1.18.3
- Tokenizers 0.11.0
- Task
- Automatic Speech Recognition
- Library
- transformers
- Type
- speech-encoder-decoder
- Created
- Mar 26, 2022
- Updated
- Mar 28, 2022