Hugging Face's logo

bhattasp
/
whisper-finetuned-all-3

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
English
whisper
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
bhattasp commited on
Commit
00d7598
•
1 Parent(s): e97e646

End of training

Browse files
Files changed (3) hide show
  1. README.md +9 -9
  2. model.safetensors +1 -1
  3. runs/Oct14_20-16-19_puranaga/events.out.tfevents.1728917194.puranaga.5935.3 +2 -2
README.md CHANGED
@@ -9,19 +9,19 @@ tags:
9
  metrics:
10
  - wer
11
  model-index:
12
- - name: bhattasp/whisper-finetuned-all-3_v2v
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
- # bhattasp/whisper-finetuned-all-3_v2v
20
 
21
  This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on the AtCO2_UWB, Atcosim, Bial dataset.
22
  It achieves the following results on the evaluation set:
23
- - Loss: 0.4279
24
- - Wer: 29.4191
25
 
26
  ## Model description
27
 
@@ -54,11 +54,11 @@ The following hyperparameters were used during training:
54
 
55
  | Training Loss | Epoch | Step | Validation Loss | Wer |
56
  |:-------------:|:-----:|:----:|:---------------:|:-------:|
57
- | 0.2288 | 1.0 | 1342 | 0.4228 | 39.1455 |
58
- | 0.173 | 2.0 | 2684 | 0.4116 | 29.0975 |
59
- | 0.1243 | 3.0 | 4026 | 0.4163 | 27.9078 |
60
- | 0.0839 | 4.0 | 5368 | 0.4222 | 29.9007 |
61
- | 0.0724 | 5.0 | 6710 | 0.4279 | 29.4191 |
62
 
63
 
64
  ### Framework versions
 
9
  metrics:
10
  - wer
11
  model-index:
12
+ - name: bhattasp/whisper-finetuned-all-3
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
+ # bhattasp/whisper-finetuned-all-3
20
 
21
  This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on the AtCO2_UWB, Atcosim, Bial dataset.
22
  It achieves the following results on the evaluation set:
23
+ - Loss: 0.3387
24
+ - Wer: 22.9038
25
 
26
  ## Model description
27
 
 
54
 
55
  | Training Loss | Epoch | Step | Validation Loss | Wer |
56
  |:-------------:|:-----:|:----:|:---------------:|:-------:|
57
+ | 0.4559 | 1.0 | 1342 | 0.4642 | 36.8026 |
58
+ | 0.2906 | 2.0 | 2684 | 0.3681 | 24.1868 |
59
+ | 0.1993 | 3.0 | 4026 | 0.3436 | 22.6871 |
60
+ | 0.1389 | 4.0 | 5368 | 0.3372 | 22.8121 |
61
+ | 0.1308 | 5.0 | 6710 | 0.3387 | 22.9038 |
62
 
63
 
64
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c8049269cc608be1da75c4be14c79229e9013ca3e594bc074ba83a7e53c75b58
3
  size 151061672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:27ba9d23e4484e745e3db7871cacfdd1d628183802ff94f37339856cf92b815f
3
  size 151061672
runs/Oct14_20-16-19_puranaga/events.out.tfevents.1728917194.puranaga.5935.3 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0a944fa51bd14599e9eb0132c6133c5b1a132c449d7fb5305f2728ad13e9a224
3
- size 53143
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:90cc62223157c1905e2cb23fb1cb1d3df6f8d2d2860aa7988eac3ef472465028
3
+ size 65209