End of training
Browse files- README.md +1 -30
- model.safetensors +2 -2
- training_args.bin +1 -1
README.md
CHANGED
@@ -8,24 +8,9 @@ tags:
|
|
8 |
- generated_from_trainer
|
9 |
datasets:
|
10 |
- AlisaMaid/aidc_test
|
11 |
-
metrics:
|
12 |
-
- wer
|
13 |
model-index:
|
14 |
- name: Whisper Small Lo - Alisa
|
15 |
-
results:
|
16 |
-
- task:
|
17 |
-
name: Automatic Speech Recognition
|
18 |
-
type: automatic-speech-recognition
|
19 |
-
dataset:
|
20 |
-
name: AIDC Test
|
21 |
-
type: AlisaMaid/aidc_test
|
22 |
-
config: default
|
23 |
-
split: None
|
24 |
-
args: 'config: lo, split: test'
|
25 |
-
metrics:
|
26 |
-
- name: Wer
|
27 |
-
type: wer
|
28 |
-
value: 235.96491228070175
|
29 |
---
|
30 |
|
31 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
@@ -34,9 +19,6 @@ should probably proofread and complete it, then remove this comment. -->
|
|
34 |
# Whisper Small Lo - Alisa
|
35 |
|
36 |
This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the AIDC Test dataset.
|
37 |
-
It achieves the following results on the evaluation set:
|
38 |
-
- Loss: 0.0002
|
39 |
-
- Wer: 235.9649
|
40 |
|
41 |
## Model description
|
42 |
|
@@ -65,17 +47,6 @@ The following hyperparameters were used during training:
|
|
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 |
-
| 0.1213 | 18.1818 | 200 | 0.0821 | 247.2953 |
|
73 |
-
| 0.0031 | 36.3636 | 400 | 0.0021 | 318.8596 |
|
74 |
-
| 0.0003 | 54.5455 | 600 | 0.0003 | 322.3684 |
|
75 |
-
| 0.0002 | 72.7273 | 800 | 0.0002 | 263.5234 |
|
76 |
-
| 0.0002 | 90.9091 | 1000 | 0.0002 | 235.9649 |
|
77 |
-
|
78 |
-
|
79 |
### Framework versions
|
80 |
|
81 |
- Transformers 4.45.2
|
|
|
8 |
- generated_from_trainer
|
9 |
datasets:
|
10 |
- AlisaMaid/aidc_test
|
|
|
|
|
11 |
model-index:
|
12 |
- name: Whisper Small Lo - Alisa
|
13 |
+
results: []
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
14 |
---
|
15 |
|
16 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
19 |
# Whisper Small Lo - Alisa
|
20 |
|
21 |
This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the AIDC Test dataset.
|
|
|
|
|
|
|
22 |
|
23 |
## Model description
|
24 |
|
|
|
47 |
- training_steps: 1000
|
48 |
- mixed_precision_training: Native AMP
|
49 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
50 |
### Framework versions
|
51 |
|
52 |
- Transformers 4.45.2
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:62ae1c6a08304aa4d460d220f36152224ef0fbe42c26ba533a2afaa67fc77b5b
|
3 |
+
size 151946424
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5368
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:86d11c32e1009c4740fd5e196e21c32d5fec0c50103b6ed85f638d965b4c8454
|
3 |
size 5368
|