Downloads · 30 days
6
25% of all-time downloads
my_awesome_asr_mind_modelv2
vicot2/my_awesome_asr_mind_modelv2
my_awesome_asr_mind_modelv2 is a automatic speech recognition model from vicot2. 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
24
Public
Parameters
315M
36.6 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors1.3 GB · 100%
At a glance
- Task
- Automatic Speech Recognition
- Library
- transformers
- License
- apache-2.0
- Model type
- wav2vec2
- Access
- Public
- Created
- Oct 12, 2024
- Updated
- Oct 12, 2024
- SHA
- 4dc40b5c
Base models
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. -->
my_awesome_asr_mind_modelv2
This model is a fine-tuned version of victor233/my_awesome_asr_mind_model on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.3495
- Wer: 0.4308
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: 16
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- 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: 500
- num_epochs: 20
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 2.5963 | 0.6873 | 100 | 8.7225 | 0.9254 |
| 1.9059 | 1.3746 | 200 | 6.2957 | 0.8917 |
| 1.761 | 2.0619 | 300 | 5.1207 | 0.8694 |
| 3.7062 | 2.7491 | 400 | 5.7936 | 0.8306 |
| 2.1085 | 3.4364 | 500 | 2.4645 | 0.8151 |
| 1.2314 | 4.1237 | 600 | 1.5185 | 0.7628 |
| 1.0258 | 4.8110 | 700 | 1.4445 | 0.7170 |
| 2.1393 | 5.4983 | 800 | 1.1892 | 0.6502 |
| 1.6539 | 6.1856 | 900 | 1.1350 | 0.6327 |
| 0.9645 | 6.8729 | 1000 | 1.0081 | 0.6165 |
| 0.5164 | 7.5601 | 1100 | 0.9348 | 0.6107 |
| 1.6793 | 8.2474 | 1200 | 0.8560 | 0.5892 |
| 1.3195 | 8.9347 | 1300 | 0.7521 | 0.5514 |
| 0.6659 | 9.6220 | 1400 | 0.6726 | 0.5342 |
| 0.4254 | 10.3093 | 1500 | 0.6283 | 0.5274 |
| 1.3252 | 10.9966 | 1600 | 0.5888 | 0.5019 |
| 1.1783 | 11.6838 | 1700 | 0.5281 | 0.4901 |
| 0.5824 | 12.3711 | 1800 | 0.5055 | 0.4884 |
| 0.2816 | 13.0584 | 1900 | 0.4628 | 0.4739 |
| 1.1641 | 13.7457 | 2000 | 0.4463 | 0.4616 |
| 1.0579 | 14.4330 | 2100 | 0.4158 | 0.4548 |
| 0.384 | 15.1203 | 2200 | 0.3986 | 0.4493 |
| 0.2741 | 15.8076 | 2300 | 0.3873 | 0.4456 |
| 1.1115 | 16.4948 | 2400 | 0.3751 | 0.4421 |
| 0.8042 | 17.1821 | 2500 | 0.3630 | 0.4371 |
| 0.4742 | 17.8694 | 2600 | 0.3574 | 0.4376 |
| 0.2946 | 18.5567 | 2700 | 0.3501 | 0.4326 |
| 1.0484 | 19.2440 | 2800 | 0.3501 | 0.4316 |
| 0.7799 | 19.9313 | 2900 | 0.3495 | 0.4308 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.4.1+cu121
- Tokenizers 0.19.1
- Task
- Automatic Speech Recognition
- Library
- transformers
- Type
- wav2vec2
- License
- apache-2.0
- Created
- Oct 12, 2024
- Updated
- Oct 12, 2024