Hugging Face's logo

rogramss
/
whisper-tiny_to_chinese_accent_ae_further_analysis

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
English
whisper
hf-asr-leaderboard
Generated from Trainer
Eval Results
Model card Files Metrics Community
rogramss commited on
Commit
3723cf9
·
verified ·
1 Parent(s): cbd99c4

End of training

Browse files
Files changed (2) hide show
  1. README.md +9 -7
  2. model.safetensors +1 -1
README.md CHANGED
@@ -8,7 +8,7 @@ tags:
8
  - hf-asr-leaderboard
9
  - generated_from_trainer
10
  datasets:
11
- - chinese_english_AE_fa
12
  metrics:
13
  - wer
14
  model-index:
@@ -19,12 +19,12 @@ model-index:
19
  type: automatic-speech-recognition
20
  dataset:
21
  name: Chinese English 'AE' Phonemes
22
- type: chinese_english_AE_fa
23
  args: 'config: default, split: test'
24
  metrics:
25
  - name: Wer
26
  type: wer
27
- value: 13.64192995346559
28
  ---
29
 
30
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -34,8 +34,8 @@ should probably proofread and complete it, then remove this comment. -->
34
 
35
  This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on the Chinese English 'AE' Phonemes dataset.
36
  It achieves the following results on the evaluation set:
37
- - Loss: 0.3203
38
- - Wer: 13.6419
39
 
40
  ## Model description
41
 
@@ -61,13 +61,15 @@ The following hyperparameters were used during training:
61
  - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
62
  - lr_scheduler_type: linear
63
  - lr_scheduler_warmup_steps: 500
64
- - num_epochs: 3
65
 
66
  ### Training results
67
 
68
  | Training Loss | Epoch | Step | Validation Loss | Wer |
69
  |:-------------:|:------:|:----:|:---------------:|:-------:|
70
- | 0.1716 | 2.0080 | 1000 | 0.3203 | 13.6419 |
 
 
71
 
72
 
73
  ### Framework versions
 
8
  - hf-asr-leaderboard
9
  - generated_from_trainer
10
  datasets:
11
+ - chinese_english_AE_fa_overfitting
12
  metrics:
13
  - wer
14
  model-index:
 
19
  type: automatic-speech-recognition
20
  dataset:
21
  name: Chinese English 'AE' Phonemes
22
+ type: chinese_english_AE_fa_overfitting
23
  args: 'config: default, split: test'
24
  metrics:
25
  - name: Wer
26
  type: wer
27
+ value: 15.33186382561842
28
  ---
29
 
30
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
34
 
35
  This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on the Chinese English 'AE' Phonemes dataset.
36
  It achieves the following results on the evaluation set:
37
+ - Loss: 0.3921
38
+ - Wer: 15.3319
39
 
40
  ## Model description
41
 
 
61
  - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
62
  - lr_scheduler_type: linear
63
  - lr_scheduler_warmup_steps: 500
64
+ - training_steps: 3000
65
 
66
  ### Training results
67
 
68
  | Training Loss | Epoch | Step | Validation Loss | Wer |
69
  |:-------------:|:------:|:----:|:---------------:|:-------:|
70
+ | 0.0616 | 2.0080 | 1000 | 0.3729 | 14.4012 |
71
+ | 0.0007 | 4.0161 | 2000 | 0.3843 | 15.0869 |
72
+ | 0.0005 | 6.0241 | 3000 | 0.3921 | 15.3319 |
73
 
74
 
75
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e929f3e88a2fb8aa01d9464caf79e77eb5c56b4ac29730487425f23c515db972
3
  size 151061672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:73f2e4ffc6c83626edf72e9c907dd8fa639b9efeaf8daf0ccf7c7f4ffb52e027
3
  size 151061672