Hugging Face's logo

devkya
/
large-v2-no-bg-v1

PEFT
PyTorch
Safetensors
whisper
Generated from Trainer
Model card Files
xet
Community
devkya commited on
Commit
49d39ad
·
verified ·
1 Parent(s): c57e93f

devkya/large-v2-no-bg-v1

Browse files
Files changed (5) hide show
  1. README.md +12 -12
  2. adapter_model.safetensors +1 -1
  3. trainer/adapter_model.safetensors +1 -1
  4. trainer/training_args.bin +1 -1
  5. training_args.bin +1 -1
README.md CHANGED
@@ -14,12 +14,12 @@ model-index:
14
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
15
  should probably proofread and complete it, then remove this comment. -->
16
 
17
- [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/xpertinc/huggingface/runs/69eh0qew)
18
  # large-v2-no-bg-v1
19
 
20
  This model is a fine-tuned version of [openai/whisper-large-v2](https://huggingface.co/openai/whisper-large-v2) on the audiofolder dataset.
21
  It achieves the following results on the evaluation set:
22
- - Loss: 0.6326
23
 
24
  ## Model description
25
 
@@ -54,16 +54,16 @@ The following hyperparameters were used during training:
54
 
55
  | Training Loss | Epoch | Step | Validation Loss |
56
  |:-------------:|:---------:|:----:|:---------------:|
57
- | 1.6386 | 142.8571 | 500 | 1.6741 |
58
- | 1.258 | 285.7143 | 1000 | 1.2448 |
59
- | 0.9484 | 428.5714 | 1500 | 0.9017 |
60
- | 0.8393 | 571.4286 | 2000 | 0.8076 |
61
- | 0.7729 | 714.2857 | 2500 | 0.7526 |
62
- | 0.7319 | 857.1429 | 3000 | 0.7090 |
63
- | 0.691 | 1000.0 | 3500 | 0.6753 |
64
- | 0.6604 | 1142.8571 | 4000 | 0.6516 |
65
- | 0.6477 | 1285.7143 | 4500 | 0.6374 |
66
- | 0.6392 | 1428.5714 | 5000 | 0.6326 |
67
 
68
 
69
  ### Framework versions
 
14
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
15
  should probably proofread and complete it, then remove this comment. -->
16
 
17
+ [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/xpertinc/huggingface/runs/4pssklsm)
18
  # large-v2-no-bg-v1
19
 
20
  This model is a fine-tuned version of [openai/whisper-large-v2](https://huggingface.co/openai/whisper-large-v2) on the audiofolder dataset.
21
  It achieves the following results on the evaluation set:
22
+ - Loss: 0.6263
23
 
24
  ## Model description
25
 
 
54
 
55
  | Training Loss | Epoch | Step | Validation Loss |
56
  |:-------------:|:---------:|:----:|:---------------:|
57
+ | 1.6361 | 142.8571 | 500 | 1.6697 |
58
+ | 1.257 | 285.7143 | 1000 | 1.2417 |
59
+ | 0.9481 | 428.5714 | 1500 | 0.8995 |
60
+ | 0.8397 | 571.4286 | 2000 | 0.8044 |
61
+ | 0.7741 | 714.2857 | 2500 | 0.7487 |
62
+ | 0.7336 | 857.1429 | 3000 | 0.7035 |
63
+ | 0.6932 | 1000.0 | 3500 | 0.6689 |
64
+ | 0.6626 | 1142.8571 | 4000 | 0.6449 |
65
+ | 0.6501 | 1285.7143 | 4500 | 0.6310 |
66
+ | 0.6413 | 1428.5714 | 5000 | 0.6263 |
67
 
68
 
69
  ### Framework versions
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1f92795914b8d6fcde00e90820af8154c6be4d54feaff41f140ebbe9c6cc58a0
3
  size 41979856
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1e8b5859c3be600a016d4eaeec6ead26e7107006993819667068b91b7a111acc
3
  size 41979856
trainer/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1f92795914b8d6fcde00e90820af8154c6be4d54feaff41f140ebbe9c6cc58a0
3
  size 41979856
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1e8b5859c3be600a016d4eaeec6ead26e7107006993819667068b91b7a111acc
3
  size 41979856
trainer/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:804b1c5d47c36e952b9421d9fc2cbe635e65852881cc23a0a72908bdb16888da
3
  size 5240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:671dbdd1b9fa50efbc2fffa6c8a30b48ba38973eaeaebcd06cae3a68f32994c6
3
  size 5240
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:804b1c5d47c36e952b9421d9fc2cbe635e65852881cc23a0a72908bdb16888da
3
  size 5240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:671dbdd1b9fa50efbc2fffa6c8a30b48ba38973eaeaebcd06cae3a68f32994c6
3
  size 5240