Yassinevic commited on
Commit
e509422
·
verified ·
1 Parent(s): e6130c1

End of training

Browse files
Files changed (3) hide show
  1. README.md +12 -13
  2. generation_config.json +1 -1
  3. model.safetensors +1 -1
README.md CHANGED
@@ -11,17 +11,17 @@ datasets:
11
  metrics:
12
  - wer
13
  model-index:
14
- - name: Whisper Tiny Ar - Yassinevic
15
  results:
16
  - task:
17
  name: Automatic Speech Recognition
18
  type: automatic-speech-recognition
19
  dataset:
20
- name: Moroccan-Darija-HSIO 0.0
21
  type: Yassinevic/Moroccan-Darija-HSIO
22
  config: default
23
  split: None
24
- args: 'config: ar, split: test'
25
  metrics:
26
  - name: Wer
27
  type: wer
@@ -31,11 +31,11 @@ model-index:
31
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
32
  should probably proofread and complete it, then remove this comment. -->
33
 
34
- # Whisper Tiny Ar - Yassinevic
35
 
36
- This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on the Moroccan-Darija-HSIO 0.0 dataset.
37
  It achieves the following results on the evaluation set:
38
- - Loss: 0.0001
39
  - Wer: 0.0
40
 
41
  ## Model description
@@ -61,19 +61,18 @@ The following hyperparameters were used during training:
61
  - seed: 42
62
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
63
  - lr_scheduler_type: linear
64
- - lr_scheduler_warmup_steps: 200
65
- - training_steps: 1000
66
  - mixed_precision_training: Native AMP
67
 
68
  ### Training results
69
 
70
  | Training Loss | Epoch | Step | Validation Loss | Wer |
71
  |:-------------:|:--------:|:----:|:---------------:|:---:|
72
- | 0.0007 | 66.6667 | 200 | 0.0007 | 0.0 |
73
- | 0.0002 | 133.3333 | 400 | 0.0002 | 0.0 |
74
- | 0.0001 | 200.0 | 600 | 0.0001 | 0.0 |
75
- | 0.0001 | 266.6667 | 800 | 0.0001 | 0.0 |
76
- | 0.0001 | 333.3333 | 1000 | 0.0001 | 0.0 |
77
 
78
 
79
  ### Framework versions
 
11
  metrics:
12
  - wer
13
  model-index:
14
+ - name: Whisper Tiny AR - Yassinevic
15
  results:
16
  - task:
17
  name: Automatic Speech Recognition
18
  type: automatic-speech-recognition
19
  dataset:
20
+ name: Moroccan Darija HSIO
21
  type: Yassinevic/Moroccan-Darija-HSIO
22
  config: default
23
  split: None
24
+ args: 'config: hi, split: test'
25
  metrics:
26
  - name: Wer
27
  type: wer
 
31
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
32
  should probably proofread and complete it, then remove this comment. -->
33
 
34
+ # Whisper Tiny AR - Yassinevic
35
 
36
+ This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on the Moroccan Darija HSIO dataset.
37
  It achieves the following results on the evaluation set:
38
+ - Loss: 0.0000
39
  - Wer: 0.0
40
 
41
  ## Model description
 
61
  - seed: 42
62
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
63
  - lr_scheduler_type: linear
64
+ - lr_scheduler_warmup_steps: 500
65
+ - training_steps: 4000
66
  - mixed_precision_training: Native AMP
67
 
68
  ### Training results
69
 
70
  | Training Loss | Epoch | Step | Validation Loss | Wer |
71
  |:-------------:|:--------:|:----:|:---------------:|:---:|
72
+ | 0.0001 | 166.6667 | 1000 | 0.0001 | 0.0 |
73
+ | 0.0 | 333.3333 | 2000 | 0.0001 | 0.0 |
74
+ | 0.0 | 500.0 | 3000 | 0.0000 | 0.0 |
75
+ | 0.0 | 666.6667 | 4000 | 0.0000 | 0.0 |
 
76
 
77
 
78
  ### Framework versions
generation_config.json CHANGED
@@ -134,7 +134,7 @@
134
  "<|yo|>": 50325,
135
  "<|zh|>": 50260
136
  },
137
- "language": "arabic",
138
  "max_initial_timestamp_index": 50,
139
  "max_length": 448,
140
  "no_timestamps_token_id": 50363,
 
134
  "<|yo|>": 50325,
135
  "<|zh|>": 50260
136
  },
137
+ "language": "Arabic",
138
  "max_initial_timestamp_index": 50,
139
  "max_length": 448,
140
  "no_timestamps_token_id": 50363,
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:449d85567fa703792f18755e346c1ed45d63bec5fdfa683319475ad79bd100ee
3
  size 151061672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:865af8df61d29d728cdbb2a9a015b63d568f588e5ef0890a41c845e9e1242eb5
3
  size 151061672