Hugging Face's logo

jun-han
/
Whisper-squeezeformer-v3

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
English
whisper
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
jun-han commited on
Commit
0f1dd86
·
verified ·
1 Parent(s): 3631ae3

Model save

Browse files
Files changed (3) hide show
  1. README.md +8 -8
  2. model.safetensors +1 -1
  3. runs/Nov28_09-29-06_DESKTOP-Q3M97DH/events.out.tfevents.1732757351.DESKTOP-Q3M97DH.30968.0 +2 -2
README.md CHANGED
@@ -1,7 +1,5 @@
1
  ---
2
  library_name: transformers
3
- language:
4
- - en
5
  license: apache-2.0
6
  base_model: openai/whisper-small
7
  tags:
@@ -9,19 +7,19 @@ tags:
9
  metrics:
10
  - wer
11
  model-index:
12
- - name: Whisper-squeezeformer-NSQU-whisper
13
  results: []
14
  ---
15
 
16
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
17
  should probably proofread and complete it, then remove this comment. -->
18
 
19
- # Whisper-squeezeformer-NSQU-whisper
20
 
21
- This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the LibriSpeech dataset.
22
  It achieves the following results on the evaluation set:
23
- - Loss: 0.1297
24
- - Wer: 5.6204
25
 
26
  ## Model description
27
 
@@ -47,7 +45,7 @@ The following hyperparameters were used during training:
47
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
48
  - lr_scheduler_type: linear
49
  - lr_scheduler_warmup_steps: 2500
50
- - training_steps: 45000
51
  - mixed_precision_training: Native AMP
52
 
53
  ### Training results
@@ -72,6 +70,8 @@ The following hyperparameters were used during training:
72
  | 0.1776 | 16.0 | 40000 | 0.1302 | 5.5995 |
73
  | 0.1416 | 17.0 | 42500 | 0.1298 | 5.6204 |
74
  | 0.1239 | 18.0 | 45000 | 0.1297 | 5.6204 |
 
 
75
 
76
 
77
  ### Framework versions
 
1
  ---
2
  library_name: transformers
 
 
3
  license: apache-2.0
4
  base_model: openai/whisper-small
5
  tags:
 
7
  metrics:
8
  - wer
9
  model-index:
10
+ - name: Whisper-squeezeformer-v3
11
  results: []
12
  ---
13
 
14
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
15
  should probably proofread and complete it, then remove this comment. -->
16
 
17
+ # Whisper-squeezeformer-v3
18
 
19
+ This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the None dataset.
20
  It achieves the following results on the evaluation set:
21
+ - Loss: 0.1322
22
+ - Wer: 5.6642
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: 2500
48
+ - training_steps: 50000
49
  - mixed_precision_training: Native AMP
50
 
51
  ### Training results
 
70
  | 0.1776 | 16.0 | 40000 | 0.1302 | 5.5995 |
71
  | 0.1416 | 17.0 | 42500 | 0.1298 | 5.6204 |
72
  | 0.1239 | 18.0 | 45000 | 0.1297 | 5.6204 |
73
+ | 0.3373 | 19.0 | 47500 | 0.1353 | 5.7403 |
74
+ | 0.2785 | 20.0 | 50000 | 0.1322 | 5.6642 |
75
 
76
 
77
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:98425eed70171f7d52bffc8ab2d2f62b8bcaeb2145a09f3db616444a1eed5d95
3
  size 1128325056
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dab8c0f9575fbbcd5a8bcd8a9c5d9cb115e91097d852c52848262942623e6c72
3
  size 1128325056
runs/Nov28_09-29-06_DESKTOP-Q3M97DH/events.out.tfevents.1732757351.DESKTOP-Q3M97DH.30968.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:375712dba79bbf0113d52959fa229dbfb4287f1215d7c3ebadd9eb7dd87be45d
3
- size 7280
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2039f99a3c25c9d1f20d3202e0eaded515bb3faacfb90ba65092732093f7163f
3
+ size 8179