Hugging Face's logo

yuweiiizz
/
whisper-small-taiwanese-lora

PEFT
TensorBoard
Safetensors
Min Nan Chinese
Generated from Trainer
Model card Files Metrics Community
yuweiiizz commited on
Commit
4eb6664
•
1 Parent(s): 270b658

End of training

Browse files
Files changed (3) hide show
  1. README.md +9 -7
  2. adapter_model.safetensors +1 -1
  3. runs/Sep07_06-04-39_b6a8975d2e62/events.out.tfevents.1725689081.b6a8975d2e62.25.0 +2 -2
README.md CHANGED
@@ -1,13 +1,13 @@
1
  ---
 
 
 
2
  language:
3
  - nan
4
- license: apache-2.0
5
  library_name: peft
 
6
  tags:
7
  - generated_from_trainer
8
- datasets:
9
- - mozilla-foundation/common_voice_16_1
10
- base_model: openai/whisper-small
11
  model-index:
12
  - name: Whisper small Taiwanese - LoRA
13
  results: []
@@ -20,7 +20,7 @@ should probably proofread and complete it, then remove this comment. -->
20
 
21
  This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the Common Voice 16.1 dataset.
22
  It achieves the following results on the evaluation set:
23
- - Loss: 0.8821
24
 
25
  ## Model description
26
 
@@ -48,7 +48,7 @@ The following hyperparameters were used during training:
48
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
49
  - lr_scheduler_type: linear
50
  - lr_scheduler_warmup_ratio: 0.1
51
- - num_epochs: 4
52
  - mixed_precision_training: Native AMP
53
 
54
  ### Training results
@@ -58,7 +58,9 @@ The following hyperparameters were used during training:
58
  | 1.0204 | 1.0 | 2572 | 1.0091 |
59
  | 0.9044 | 2.0 | 5144 | 0.9392 |
60
  | 0.7166 | 3.0 | 7716 | 0.8862 |
61
- | 0.4918 | 4.0 | 10288 | 0.8821 |
 
 
62
 
63
 
64
  ### Framework versions
 
1
  ---
2
+ base_model: openai/whisper-small
3
+ datasets:
4
+ - mozilla-foundation/common_voice_16_1
5
  language:
6
  - nan
 
7
  library_name: peft
8
+ license: apache-2.0
9
  tags:
10
  - generated_from_trainer
 
 
 
11
  model-index:
12
  - name: Whisper small Taiwanese - LoRA
13
  results: []
 
20
 
21
  This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the Common Voice 16.1 dataset.
22
  It achieves the following results on the evaluation set:
23
+ - Loss: 0.8997
24
 
25
  ## Model description
26
 
 
48
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
49
  - lr_scheduler_type: linear
50
  - lr_scheduler_warmup_ratio: 0.1
51
+ - num_epochs: 6
52
  - mixed_precision_training: Native AMP
53
 
54
  ### Training results
 
58
  | 1.0204 | 1.0 | 2572 | 1.0091 |
59
  | 0.9044 | 2.0 | 5144 | 0.9392 |
60
  | 0.7166 | 3.0 | 7716 | 0.8862 |
61
+ | 0.5224 | 4.0 | 10288 | 0.9016 |
62
+ | 0.5268 | 5.0 | 12860 | 0.8868 |
63
+ | 0.3808 | 6.0 | 15432 | 0.8997 |
64
 
65
 
66
  ### Framework versions
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5330e78a268c0a3a4f1bc5179ee98f12e3b600fb81a24915b0d5276a73ad4dbf
3
  size 19548472
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:37e0f3bb11e29c4fbde09a832cb7645156080ef5b843419f97e5cda4872b90a3
3
  size 19548472
runs/Sep07_06-04-39_b6a8975d2e62/events.out.tfevents.1725689081.b6a8975d2e62.25.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fb9d7e07c8c19df83a8db351940f318a3380c7bbca6f7faf4ccef900de359d42
3
- size 48199
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2472e296eb99f42c54bd92f56ccff221b365206c32f5690d56aa6004f6b09754
3
+ size 52411