Downloads · 30 days
9
17% of all-time downloads
xlsr-finetuned
mempal/xlsr-finetuned
xlsr-finetuned is a automatic speech recognition model from mempal. 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
52
Public
Repo size
5.8 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
- Model type
- wav2vec2
- Access
- Public
- Created
- Aug 13, 2023
- Updated
- Aug 16, 2023
- SHA
- 2cff6932
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. -->
xlsr-finetuned
This model is a fine-tuned version of classla/wav2vec2-xls-r-parlaspeech-hr on the audiofolder dataset. It achieves the following results on the evaluation set:
- Loss: 2.1218
- Wer: 1.0
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: 4
- 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: 1
- training_steps: 4
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| No log | 1.0 | 1 | 14.0503 | 20.0 |
| 3.5057 | 2.0 | 2 | 5.3734 | 4.0 |
| 3.5057 | 3.0 | 3 | 2.8914 | 1.0 |
| 1.0014 | 4.0 | 4 | 2.1218 | 1.0 |
Framework versions
- Transformers 4.31.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.4
- Tokenizers 0.13.3
- Task
- Automatic Speech Recognition
- Library
- transformers
- Type
- wav2vec2
- Created
- Aug 13, 2023
- Updated
- Aug 16, 2023