Downloads · 30 days
25
23% of all-time downloads
wav2vec2-2-rnd
sanchit-gandhi/wav2vec2-2-rnd
wav2vec2-2-rnd 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
107
Public
Repo size
49.5 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin4.4 GB · 77%
At a glance
- Task
- Automatic Speech Recognition
- Library
- transformers
- Model type
- speech-encoder-decoder
- Access
- Public
- Created
- Mar 6, 2022
- Updated
- Mar 8, 2022
- SHA
- 6d4ae6ed
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: 0.9599
- Wer: 0.1442
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: 4
- 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: 1000
- num_epochs: 20.0
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 6.1431 | 1.68 | 1500 | 6.0870 | 1.4277 |
| 5.498 | 3.36 | 3000 | 5.5505 | 1.6318 |
| 3.575 | 5.04 | 4500 | 3.7856 | 0.6683 |
| 1.7532 | 6.73 | 6000 | 2.4603 | 0.3576 |
| 1.6379 | 8.41 | 7500 | 1.8847 | 0.2932 |
| 1.3145 | 10.09 | 9000 | 1.5027 | 0.2222 |
| 0.8389 | 11.77 | 10500 | 1.2637 | 0.1855 |
| 0.9239 | 13.45 | 12000 | 1.1424 | 0.1683 |
| 0.6666 | 15.13 | 13500 | 1.0562 | 0.1593 |
| 0.5258 | 16.82 | 15000 | 0.9911 | 0.1489 |
| 0.4733 | 18.5 | 16500 | 0.9599 | 0.1442 |
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 6, 2022
- Updated
- Mar 8, 2022