Hugging Face's logo

Hiro-nguyen
/
whisper-small-hi

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
English
whisper
hf-asr-leaderboard
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
Hiro-nguyen commited on
Commit
feb112a
·
verified ·
1 Parent(s): 0d7adbd

Model save

Browse files
Files changed (4) hide show
  1. README.md +18 -21
  2. generation_config.json +1 -1
  3. model.safetensors +1 -1
  4. runs/Jun12_04-50-22_z390-a/events.out.tfevents.1718168043.z390-a.568.0 +2 -2
README.md CHANGED
@@ -1,27 +1,24 @@
1
  ---
2
- language:
3
- - en
4
  license: apache-2.0
5
  base_model: openai/whisper-medium.en
6
  tags:
7
- - hf-asr-leaderboard
8
  - generated_from_trainer
9
  metrics:
10
  - wer
11
  model-index:
12
- - name: Whisper Base EN
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 Base EN
20
 
21
- This model is a fine-tuned version of [openai/whisper-medium.en](https://huggingface.co/openai/whisper-medium.en) on the ADLINK dataset.
22
  It achieves the following results on the evaluation set:
23
  - Loss: 0.0003
24
- - Wer: 448.7879
25
 
26
  ## Model description
27
 
@@ -52,23 +49,23 @@ The following hyperparameters were used during training:
52
 
53
  ### Training results
54
 
55
- | Training Loss | Epoch | Step | Validation Loss | Wer |
56
- |:-------------:|:-----:|:----:|:---------------:|:--------:|
57
- | 1.1004 | 25.0 | 100 | 1.0484 | 2.1212 |
58
- | 0.3934 | 50.0 | 200 | 0.4056 | 45.7576 |
59
- | 0.0206 | 75.0 | 300 | 0.0131 | 63.3333 |
60
- | 0.0012 | 100.0 | 400 | 0.0012 | 280.0 |
61
- | 0.0006 | 125.0 | 500 | 0.0006 | 319.6970 |
62
- | 0.0004 | 150.0 | 600 | 0.0004 | 381.5152 |
63
- | 0.0003 | 175.0 | 700 | 0.0003 | 380.0 |
64
- | 0.0003 | 200.0 | 800 | 0.0003 | 497.8788 |
65
- | 0.0003 | 225.0 | 900 | 0.0003 | 462.7273 |
66
- | 0.0003 | 250.0 | 1000 | 0.0003 | 448.7879 |
67
 
68
 
69
  ### Framework versions
70
 
71
- - Transformers 4.41.1
72
  - Pytorch 2.3.0a0+ebedce2
73
- - Datasets 2.19.1
74
  - Tokenizers 0.19.1
 
1
  ---
 
 
2
  license: apache-2.0
3
  base_model: openai/whisper-medium.en
4
  tags:
 
5
  - generated_from_trainer
6
  metrics:
7
  - wer
8
  model-index:
9
+ - name: whisper-small-hi
10
  results: []
11
  ---
12
 
13
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
14
  should probably proofread and complete it, then remove this comment. -->
15
 
16
+ # whisper-small-hi
17
 
18
+ This model is a fine-tuned version of [openai/whisper-medium.en](https://huggingface.co/openai/whisper-medium.en) on the None dataset.
19
  It achieves the following results on the evaluation set:
20
  - Loss: 0.0003
21
+ - Wer: 1.5152
22
 
23
  ## Model description
24
 
 
49
 
50
  ### Training results
51
 
52
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
53
+ |:-------------:|:-----:|:----:|:---------------:|:------:|
54
+ | 1.0495 | 25.0 | 100 | 1.0270 | 2.1212 |
55
+ | 0.3802 | 50.0 | 200 | 0.3923 | 1.8182 |
56
+ | 0.0205 | 75.0 | 300 | 0.0130 | 1.8182 |
57
+ | 0.0012 | 100.0 | 400 | 0.0012 | 0.9091 |
58
+ | 0.0006 | 125.0 | 500 | 0.0006 | 0.9091 |
59
+ | 0.0004 | 150.0 | 600 | 0.0004 | 0.9091 |
60
+ | 0.0003 | 175.0 | 700 | 0.0003 | 0.9091 |
61
+ | 0.0003 | 200.0 | 800 | 0.0003 | 2.1212 |
62
+ | 0.0003 | 225.0 | 900 | 0.0003 | 2.1212 |
63
+ | 0.0003 | 250.0 | 1000 | 0.0003 | 1.5152 |
64
 
65
 
66
  ### Framework versions
67
 
68
+ - Transformers 4.41.2
69
  - Pytorch 2.3.0a0+ebedce2
70
+ - Datasets 2.19.2
71
  - Tokenizers 0.19.1
generation_config.json CHANGED
@@ -185,5 +185,5 @@
185
  50360,
186
  50361
187
  ],
188
- "transformers_version": "4.41.1"
189
  }
 
185
  50360,
186
  50361
187
  ],
188
+ "transformers_version": "4.41.2"
189
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4b667dccfa23d87a453cac6ec5a3f2a96d76b825760aa80b9e33a1ea8f21e296
3
  size 3055540208
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:84e4afa2faec1f795151faedbfeeff1302144c20c2847ef638887e5664899c5f
3
  size 3055540208
runs/Jun12_04-50-22_z390-a/events.out.tfevents.1718168043.z390-a.568.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:66054fb65e5515ad232929a74f5e3e370bfdb32fb50f07e68bd316098e3fe4ba
3
- size 13702
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d4ce8c7b5e069d3e50e73ae599a025e8b5ef0034774fd649fdc4b0c20bfa0743
3
+ size 17542