Hugging Face's logo

breco
/
whisper-tiny-few-audios

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
Spanish
whisper
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
breco commited on
Commit
d9d1922
·
verified ·
1 Parent(s): 2e95eec

Model save

Browse files
Files changed (3) hide show
  1. README.md +19 -19
  2. generation_config.json +0 -10
  3. model.safetensors +1 -1
README.md CHANGED
@@ -1,7 +1,5 @@
1
  ---
2
  library_name: transformers
3
- language:
4
- - spa
5
  license: apache-2.0
6
  base_model: openai/whisper-tiny
7
  tags:
@@ -9,19 +7,19 @@ tags:
9
  metrics:
10
  - wer
11
  model-index:
12
- - name: Whisper Tiny Few Audios - vfranchis
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 Tiny Few Audios - vfranchis
20
 
21
- This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on the Few audios 1.0 dataset.
22
  It achieves the following results on the evaluation set:
23
  - Loss: nan
24
- - Wer: 88.8889
25
 
26
  ## Model description
27
 
@@ -41,9 +39,11 @@ More information needed
41
 
42
  The following hyperparameters were used during training:
43
  - learning_rate: 1e-05
44
- - train_batch_size: 16
45
  - eval_batch_size: 8
46
  - seed: 42
 
 
47
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
48
  - lr_scheduler_type: linear
49
  - lr_scheduler_warmup_steps: 10
@@ -52,18 +52,18 @@ The following hyperparameters were used during training:
52
 
53
  ### Training results
54
 
55
- | Training Loss | Epoch | Step | Validation Loss | Wer |
56
- |:-------------:|:-----:|:----:|:---------------:|:-------:|
57
- | 0.0 | 2.5 | 10 | nan | 88.8889 |
58
- | 0.0 | 5.0 | 20 | nan | 88.8889 |
59
- | 0.0 | 7.5 | 30 | nan | 88.8889 |
60
- | 0.0 | 10.0 | 40 | nan | 88.8889 |
61
- | 0.0 | 12.5 | 50 | nan | 88.8889 |
62
- | 0.0 | 15.0 | 60 | nan | 88.8889 |
63
- | 0.0 | 17.5 | 70 | nan | 88.8889 |
64
- | 0.0 | 20.0 | 80 | nan | 88.8889 |
65
- | 0.0 | 22.5 | 90 | nan | 88.8889 |
66
- | 0.0 | 25.0 | 100 | nan | 88.8889 |
67
 
68
 
69
  ### Framework versions
 
1
  ---
2
  library_name: transformers
 
 
3
  license: apache-2.0
4
  base_model: openai/whisper-tiny
5
  tags:
 
7
  metrics:
8
  - wer
9
  model-index:
10
+ - name: whisper-tiny-few-audios
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-tiny-few-audios
18
 
19
+ This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on the None dataset.
20
  It achieves the following results on the evaluation set:
21
  - Loss: nan
22
+ - Wer: 100.0
23
 
24
  ## Model description
25
 
 
39
 
40
  The following hyperparameters were used during training:
41
  - learning_rate: 1e-05
42
+ - train_batch_size: 4
43
  - eval_batch_size: 8
44
  - seed: 42
45
+ - gradient_accumulation_steps: 4
46
+ - total_train_batch_size: 16
47
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
48
  - lr_scheduler_type: linear
49
  - lr_scheduler_warmup_steps: 10
 
52
 
53
  ### Training results
54
 
55
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
56
+ |:-------------:|:-------:|:----:|:---------------:|:-------:|
57
+ | 2.5797 | 3.0769 | 10 | nan | 83.3333 |
58
+ | 1.45 | 6.1538 | 20 | nan | 58.3333 |
59
+ | 0.5973 | 9.2308 | 30 | nan | 33.3333 |
60
+ | 0.234 | 12.3077 | 40 | nan | 33.3333 |
61
+ | 0.1089 | 15.3846 | 50 | nan | 25.0 |
62
+ | 0.052 | 18.4615 | 60 | nan | 33.3333 |
63
+ | 0.0425 | 21.5385 | 70 | nan | 33.3333 |
64
+ | 0.2025 | 24.6154 | 80 | nan | 50.0 |
65
+ | 1.957 | 27.6923 | 90 | nan | 100.0 |
66
+ | 6.8512 | 30.7692 | 100 | nan | 100.0 |
67
 
68
 
69
  ### Framework versions
generation_config.json CHANGED
@@ -32,16 +32,6 @@
32
  "bos_token_id": 50257,
33
  "decoder_start_token_id": 50258,
34
  "eos_token_id": 50257,
35
- "forced_decoder_ids": [
36
- [
37
- 1,
38
- null
39
- ],
40
- [
41
- 2,
42
- 50359
43
- ]
44
- ],
45
  "is_multilingual": true,
46
  "lang_to_id": {
47
  "<|af|>": 50327,
 
32
  "bos_token_id": 50257,
33
  "decoder_start_token_id": 50258,
34
  "eos_token_id": 50257,
 
 
 
 
 
 
 
 
 
 
35
  "is_multilingual": true,
36
  "lang_to_id": {
37
  "<|af|>": 50327,
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8e7b6ed06d265b0728700630ec99d7235ea27dcee4d55fdc67bf549a3fc2cc8e
3
  size 151061672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:136e7e270714a45fb455ff85c577215376bab8a5cf54c94fdf07f350602ac6e1
3
  size 151061672