Hugging Face's logo

jimjakdiend
/
distilwhisper_finetune

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
whisper
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
jimjakdiend commited on
Commit
726a713
•
1 Parent(s): 3cb5768

Training in progress, step 250

Browse files
Files changed (5) hide show
  1. README.md +8 -8
  2. model.safetensors +1 -1
  3. runs/May21_07-37-18_a643b53be258/events.out.tfevents.1716277040.a643b53be258.9776.0 +3 -0
  4. runs/May21_08-05-47_a643b53be258/events.out.tfevents.1716278749.a643b53be258.17432.0 +3 -0
  5. training_args.bin +1 -1
README.md CHANGED
@@ -15,13 +15,13 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  This model is a fine-tuned version of [distil-whisper/distil-large-v3](https://huggingface.co/distil-whisper/distil-large-v3) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
- - eval_loss: 0.7639
19
- - eval_wer: 30.1396
20
- - eval_runtime: 848.6992
21
  - eval_samples_per_second: 0.825
22
  - eval_steps_per_second: 0.104
23
- - epoch: 0.1143
24
- - step: 20
25
 
26
  ## Model description
27
 
@@ -41,13 +41,13 @@ More information needed
41
 
42
  The following hyperparameters were used during training:
43
  - learning_rate: 1e-05
44
- - train_batch_size: 16
45
  - eval_batch_size: 8
46
  - seed: 42
47
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
48
  - lr_scheduler_type: linear
49
- - lr_scheduler_warmup_steps: 500
50
- - training_steps: 5000
51
  - mixed_precision_training: Native AMP
52
 
53
  ### Framework versions
 
15
 
16
  This model is a fine-tuned version of [distil-whisper/distil-large-v3](https://huggingface.co/distil-whisper/distil-large-v3) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
+ - eval_loss: 0.0432
19
+ - eval_wer: 3.2604
20
+ - eval_runtime: 848.1823
21
  - eval_samples_per_second: 0.825
22
  - eval_steps_per_second: 0.104
23
+ - epoch: 1.7857
24
+ - step: 250
25
 
26
  ## Model description
27
 
 
41
 
42
  The following hyperparameters were used during training:
43
  - learning_rate: 1e-05
44
+ - train_batch_size: 20
45
  - eval_batch_size: 8
46
  - seed: 42
47
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
48
  - lr_scheduler_type: linear
49
+ - lr_scheduler_warmup_steps: 100
50
+ - training_steps: 1000
51
  - mixed_precision_training: Native AMP
52
 
53
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:316c91d4a31204de325f265c4e68315ac453f7b3e11b903e26f47ac954ad61a7
3
  size 3025686376
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d91e527690236d4ca8c8806f1ce5f781656d0f424d77f448e223f4a076d37050
3
  size 3025686376
runs/May21_07-37-18_a643b53be258/events.out.tfevents.1716277040.a643b53be258.9776.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8c2ae42d4459ce2961a564e27842868db5d808e8faed729fe48c2abff90bc610
3
+ size 6342
runs/May21_08-05-47_a643b53be258/events.out.tfevents.1716278749.a643b53be258.17432.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:afc982c306197be0dd8c3cacbefe1a3570bb61d979c09b1cfdc99665f90d1076
3
+ size 8025
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2beaff75246f3620503c5354b62b0e0960635d663b1544def8cbe2bd67705554
3
  size 5240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aaabfc39883a9199b40168a22600d141735fd48c45e75ec4efb0bccd53407c8e
3
  size 5240