Hugging Face's logo

world-of-june
/
distil-medium.en-ft-kws-speech-commands

Audio Classification
Transformers
TensorBoard
Safetensors
whisper
Generated from Trainer
Eval Results
Model card Files
xet
Metrics Community
world-of-june commited on
Commit
56a2f40
·
verified ·
1 Parent(s): 26d2198

End of training

Browse files
Files changed (3) hide show
  1. README.md +17 -10
  2. model.safetensors +1 -1
  3. runs/Jan19_07-51-59_753cce8bba62/events.out.tfevents.1737273125.753cce8bba62 +2 -2
README.md CHANGED
@@ -33,7 +33,7 @@ should probably proofread and complete it, then remove this comment. -->
33
 
34
  This model is a fine-tuned version of [distil-whisper/distil-medium.en](https://huggingface.co/distil-whisper/distil-medium.en) on the Speech Commands dataset.
35
  It achieves the following results on the evaluation set:
36
- - Loss: 0.8469
37
  - Accuracy: 0.8067
38
 
39
  ## Model description
@@ -58,22 +58,29 @@ The following hyperparameters were used during training:
58
  - eval_batch_size: 8
59
  - seed: 42
60
  - distributed_type: multi-GPU
61
- - num_devices: 2
62
- - total_train_batch_size: 16
63
- - total_eval_batch_size: 16
64
  - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
65
  - lr_scheduler_type: linear
66
  - lr_scheduler_warmup_ratio: 0.1
67
- - num_epochs: 3
68
  - mixed_precision_training: Native AMP
69
 
70
  ### Training results
71
 
72
- | Training Loss | Epoch | Step | Validation Loss | Accuracy |
73
- |:-------------:|:-----:|:----:|:---------------:|:--------:|
74
- | 0.0756 | 1.0 | 2472 | 0.8973 | 0.8022 |
75
- | 0.1314 | 2.0 | 4944 | 0.8968 | 0.8035 |
76
- | 0.0244 | 3.0 | 7416 | 0.8469 | 0.8067 |
 
 
 
 
 
 
 
77
 
78
 
79
  ### Framework versions
 
33
 
34
  This model is a fine-tuned version of [distil-whisper/distil-medium.en](https://huggingface.co/distil-whisper/distil-medium.en) on the Speech Commands dataset.
35
  It achieves the following results on the evaluation set:
36
+ - Loss: 1.6851
37
  - Accuracy: 0.8067
38
 
39
  ## Model description
 
58
  - eval_batch_size: 8
59
  - seed: 42
60
  - distributed_type: multi-GPU
61
+ - num_devices: 4
62
+ - total_train_batch_size: 32
63
+ - total_eval_batch_size: 32
64
  - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
65
  - lr_scheduler_type: linear
66
  - lr_scheduler_warmup_ratio: 0.1
67
+ - num_epochs: 10
68
  - mixed_precision_training: Native AMP
69
 
70
  ### Training results
71
 
72
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
73
+ |:-------------:|:-----:|:-----:|:---------------:|:--------:|
74
+ | 0.1179 | 1.0 | 1236 | 0.8986 | 0.7990 |
75
+ | 0.1177 | 2.0 | 2472 | 0.8863 | 0.8008 |
76
+ | 0.0953 | 3.0 | 3708 | 0.9958 | 0.8031 |
77
+ | 0.1288 | 4.0 | 4944 | 1.0659 | 0.8017 |
78
+ | 0.0575 | 5.0 | 6180 | 1.1709 | 0.8026 |
79
+ | 0.0011 | 6.0 | 7416 | 1.1123 | 0.8049 |
80
+ | 0.0005 | 7.0 | 8652 | 1.2285 | 0.8049 |
81
+ | 0.0006 | 8.0 | 9888 | 1.3904 | 0.8058 |
82
+ | 0.001 | 9.0 | 11124 | 1.4603 | 0.8067 |
83
+ | 0.0001 | 10.0 | 12360 | 1.6851 | 0.8067 |
84
 
85
 
86
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:72648d896f600394186e66133250b849a7179f45ea2970062cb4a42b7f074f00
3
  size 1229992856
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0140c740f44b26757ecec7dada96c3b419630836de6e813e8559785896d89408
3
  size 1229992856
runs/Jan19_07-51-59_753cce8bba62/events.out.tfevents.1737273125.753cce8bba62 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a18a36b7a12cf857176225a8094c10c40a904f55a4e1bddc0f42fd39e0c87063
3
- size 532186
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2eaf549b8f6bcac33b284d97290ef0e271f2aaed64b94b1eb5e7671415471e60
3
+ size 533074