Downloads · 30 days
252
2% of all-time downloads
wav2vec2-large-english-phoneme-v2
speech31/wav2vec2-large-english-phoneme-v2
wav2vec2-large-english-phoneme-v2 is a automatic speech recognition model from speech31. 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
14.2K
Public
Repo size
2.5 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
- Sep 17, 2022
- Updated
- May 26, 2023
- SHA
- c5628365
Spaces
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-base960-english-phoneme_v2
This model is a fine-tuned version of facebook/wav2vec2-large on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.4069
- Cer: 0.0900
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: 32
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 1000
- num_epochs: 50
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Cer |
|---|---|---|---|---|
| 2.18 | 6.94 | 500 | 0.3118 | 0.0923 |
| 0.2622 | 13.88 | 1000 | 0.4387 | 0.1218 |
| 0.2145 | 20.83 | 1500 | 0.4441 | 0.1121 |
| 0.1429 | 27.77 | 2000 | 0.4001 | 0.1045 |
| 0.0927 | 34.72 | 2500 | 0.4692 | 0.1062 |
| 0.0598 | 41.66 | 3000 | 0.3960 | 0.0971 |
| 0.0356 | 48.61 | 3500 | 0.4069 | 0.0900 |
Framework versions
- Transformers 4.23.0.dev0
- Pytorch 1.12.1.post201
- Datasets 2.5.2.dev0
- Tokenizers 0.12.1
- Task
- Automatic Speech Recognition
- Library
- transformers
- Type
- wav2vec2
- License
- apache-2.0
- Created
- Sep 17, 2022
- Updated
- May 26, 2023