Hugging Face's logo

johnatanebonilla
/
w_large

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
whisper
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
johnatanebonilla commited on
Commit
851562c
·
verified ·
1 Parent(s): 0bd3774

Model save

Browse files
Files changed (4) hide show
  1. README.md +7 -3
  2. model-00001-of-00002.safetensors +1 -1
  3. model-00002-of-00002.safetensors +1 -1
  4. runs/Oct03_03-32-15_register-workstation-ssh/events.out.tfevents.1727926516.register-workstation-ssh.3080859.2 +2 -2
README.md CHANGED
@@ -18,8 +18,8 @@ should probably proofread and complete it, then remove this comment. -->
18
 
19
  This model is a fine-tuned version of [openai/whisper-large](https://huggingface.co/openai/whisper-large) on an unknown dataset.
20
  It achieves the following results on the evaluation set:
21
- - Loss: 0.6144
22
- - Wer: 69.9421
23
 
24
  ## Model description
25
 
@@ -45,7 +45,7 @@ The following hyperparameters were used during training:
45
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
46
  - lr_scheduler_type: linear
47
  - lr_scheduler_warmup_steps: 500
48
- - training_steps: 4000
49
  - mixed_precision_training: Native AMP
50
 
51
  ### Training results
@@ -56,6 +56,10 @@ The following hyperparameters were used during training:
56
  | 0.6638 | 0.9095 | 2000 | 0.6496 | 82.4336 |
57
  | 0.413 | 1.3643 | 3000 | 0.6292 | 76.3384 |
58
  | 0.4303 | 1.8190 | 4000 | 0.6144 | 69.9421 |
 
 
 
 
59
 
60
 
61
  ### Framework versions
 
18
 
19
  This model is a fine-tuned version of [openai/whisper-large](https://huggingface.co/openai/whisper-large) on an unknown dataset.
20
  It achieves the following results on the evaluation set:
21
+ - Loss: 0.7156
22
+ - Wer: 66.4973
23
 
24
  ## Model description
25
 
 
45
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
46
  - lr_scheduler_type: linear
47
  - lr_scheduler_warmup_steps: 500
48
+ - num_epochs: 4
49
  - mixed_precision_training: Native AMP
50
 
51
  ### Training results
 
56
  | 0.6638 | 0.9095 | 2000 | 0.6496 | 82.4336 |
57
  | 0.413 | 1.3643 | 3000 | 0.6292 | 76.3384 |
58
  | 0.4303 | 1.8190 | 4000 | 0.6144 | 69.9421 |
59
+ | 0.3339 | 2.2738 | 5000 | 0.6557 | 71.5521 |
60
+ | 0.3224 | 2.7285 | 6000 | 0.6553 | 63.5360 |
61
+ | 0.1991 | 3.1833 | 7000 | 0.7058 | 64.2753 |
62
+ | 0.1752 | 3.6380 | 8000 | 0.7156 | 66.4973 |
63
 
64
 
65
  ### Framework versions
model-00001-of-00002.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a59f4d47fe94e8111ca324263ea6a4211f6b924735e5db32103756d928dac1a5
3
  size 4992706480
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:28f6d50d150e600d2d499ddc976abea7c02782c08c822606f8abd9902c2fc5f3
3
  size 4992706480
model-00002-of-00002.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bb7165d879bb2002920198f5b43b363fcb1213c0ecce18c441c8190e3875c2a0
3
  size 1180663192
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9bdc61a426aa3250896b49507aefa12e09f11f85bb1035f90907f3f173a4f1b9
3
  size 1180663192
runs/Oct03_03-32-15_register-workstation-ssh/events.out.tfevents.1727926516.register-workstation-ssh.3080859.2 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2bb8c3cbd3cb9977ef46375dafc51d9654a3dc02152304c51601ac48df6493f5
3
- size 47450
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ecfa4e5716e11ddb651756b2d57d343f9de8ab4133d8ba9f4c003f7b0e9a1dec
3
+ size 47804