Downloads · 30 days
9
24% of all-time downloads
wav2vec2-large-960h-gs-xs-google-colab
bASILgIL/wav2vec2-large-960h-gs-xs-google-colab
wav2vec2-large-960h-gs-xs-google-colab is a automatic speech recognition model from bASILgIL. 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
38
Public
Parameters
94.4M
378 MB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors378 MB · 100%
At a glance
- Task
- Automatic Speech Recognition
- Library
- transformers
- License
- apache-2.0
- Model type
- wav2vec2
- Access
- Public
- Created
- Apr 2, 2025
- Updated
- Apr 3, 2025
- SHA
- 4e163f6b
Base models
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-960h-gs-xs-google-colab
This model is a fine-tuned version of facebook/wav2vec2-base on the gigaspeech dataset. It achieves the following results on the evaluation set:
- Loss: 1.1191
- Wer: 0.6008
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: 1e-05
- train_batch_size: 1
- eval_batch_size: 1
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 4
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 200
- num_epochs: 5
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 1.8779 | 1.0 | 1509 | 1.6399 | 0.8584 |
| 1.3401 | 2.0 | 3018 | 1.3178 | 0.7103 |
| 1.1538 | 3.0 | 4527 | 1.1959 | 0.6466 |
| 1.0593 | 4.0 | 6036 | 1.1404 | 0.6106 |
| 1.0193 | 4.9972 | 7540 | 1.1191 | 0.6008 |
Framework versions
- Transformers 4.50.3
- Pytorch 2.6.0+cu124
- Datasets 3.5.0
- Tokenizers 0.21.1
- Task
- Automatic Speech Recognition
- Library
- transformers
- Type
- wav2vec2
- License
- apache-2.0
- Created
- Apr 2, 2025
- Updated
- Apr 3, 2025