Hugging Face's logo

jethrowang
/
vanilla-whisper-tiny_evaluated_on_iOS

TensorBoard
Safetensors
Chinese
whisper
Generated from Trainer
Model card Files Metrics Community
jethrowang commited on
Commit
46e9404
•
1 Parent(s): 22abb77

End of training

Browse files
Files changed (5) hide show
  1. README.md +8 -8
  2. config.json +1 -1
  3. model.safetensors +1 -1
  4. runs/Aug11_21-08-07_SOTA/events.out.tfevents.1723382721.SOTA.1071270.0 +3 -0
  5. training_args.bin +1 -1
README.md CHANGED
@@ -19,11 +19,11 @@ should probably proofread and complete it, then remove this comment. -->
19
 
20
  This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on the HAT ASR Aligned dataset.
21
  It achieves the following results on the evaluation set:
22
- - eval_loss: 0.1439
23
- - eval_cer: 7.3919
24
- - eval_runtime: 1071.9942
25
- - eval_samples_per_second: 4.253
26
- - eval_steps_per_second: 0.133
27
  - step: 0
28
 
29
  ## Model description
@@ -43,14 +43,14 @@ More information needed
43
  ### Training hyperparameters
44
 
45
  The following hyperparameters were used during training:
46
- - learning_rate: 1e-05
47
  - train_batch_size: 64
48
  - eval_batch_size: 32
49
  - seed: 42
50
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
51
  - lr_scheduler_type: linear
52
- - lr_scheduler_warmup_steps: 488
53
- - training_steps: 4880
54
  - mixed_precision_training: Native AMP
55
 
56
  ### Framework versions
 
19
 
20
  This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on the HAT ASR Aligned dataset.
21
  It achieves the following results on the evaluation set:
22
+ - eval_loss: 0.0568
23
+ - eval_cer: 2.5256
24
+ - eval_runtime: 1031.73
25
+ - eval_samples_per_second: 4.419
26
+ - eval_steps_per_second: 0.139
27
  - step: 0
28
 
29
  ## Model description
 
43
  ### Training hyperparameters
44
 
45
  The following hyperparameters were used during training:
46
+ - learning_rate: 0.0001
47
  - train_batch_size: 64
48
  - eval_batch_size: 32
49
  - seed: 42
50
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
51
  - lr_scheduler_type: linear
52
+ - lr_scheduler_warmup_steps: 1521
53
+ - training_steps: 15210
54
  - mixed_precision_training: Native AMP
55
 
56
  ### Framework versions
config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "/share/nas169/jethrowang/CADA-GAN/whisper/results/vanilla-whisper-tiny/checkpoint-4880",
3
  "activation_dropout": 0.0,
4
  "activation_function": "gelu",
5
  "apply_spec_augment": false,
 
1
  {
2
+ "_name_or_path": "/share/nas169/jethrowang/CADA-GAN/whisper/results/vanilla-whisper-tiny/checkpoint-15210",
3
  "activation_dropout": 0.0,
4
  "activation_function": "gelu",
5
  "apply_spec_augment": false,
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:af3b70da711d292509c0735717c4408bd29b58948ebcee64d3989edb83923a4c
3
  size 151061672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8e02ab59fc94e9b47d4b163f03c542f1257531276ed4f5742863ec34f8319fb9
3
  size 151061672
runs/Aug11_21-08-07_SOTA/events.out.tfevents.1723382721.SOTA.1071270.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cada31dfb35e6bb8beb248ea2ffd16d5bd7de7eabcb265fa5f406741722bea1a
3
+ size 341
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:606d3441b0e9bda22c1a26e0f63fb003df959a90f35448a7b89d2891d3223568
3
  size 5304
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:14aa37c71a9a1a0b882d9f063fd81f33ed887ac4053e7038fd4ef0e42980c8f5
3
  size 5304