Hiro-nguyen
commited on
Commit
•
4eab9a9
1
Parent(s):
c17e695
End of training
Browse files- README.md +0 -21
- model.safetensors +1 -1
- training_args.bin +1 -1
README.md
CHANGED
@@ -6,8 +6,6 @@ base_model: openai/whisper-base.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: []
|
@@ -19,9 +17,6 @@ should probably proofread and complete it, then remove this comment. -->
|
|
19 |
# Whisper Base EN
|
20 |
|
21 |
This model is a fine-tuned version of [openai/whisper-base.en](https://huggingface.co/openai/whisper-base.en) on the ADLINK dataset.
|
22 |
-
It achieves the following results on the evaluation set:
|
23 |
-
- Loss: 0.0003
|
24 |
-
- Wer: 1.2422
|
25 |
|
26 |
## Model description
|
27 |
|
@@ -49,22 +44,6 @@ The following hyperparameters were used during training:
|
|
49 |
- lr_scheduler_warmup_steps: 500
|
50 |
- training_steps: 1000
|
51 |
|
52 |
-
### Training results
|
53 |
-
|
54 |
-
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
55 |
-
|:-------------:|:------:|:----:|:---------------:|:------:|
|
56 |
-
| 1.4205 | 33.33 | 100 | 1.0960 | 9.9379 |
|
57 |
-
| 0.4057 | 66.67 | 200 | 0.3715 | 1.5528 |
|
58 |
-
| 0.0908 | 100.0 | 300 | 0.0704 | 1.5528 |
|
59 |
-
| 0.0053 | 133.33 | 400 | 0.0037 | 1.5528 |
|
60 |
-
| 0.0011 | 166.67 | 500 | 0.0010 | 1.2422 |
|
61 |
-
| 0.0006 | 200.0 | 600 | 0.0006 | 1.2422 |
|
62 |
-
| 0.0004 | 233.33 | 700 | 0.0004 | 1.2422 |
|
63 |
-
| 0.0003 | 266.67 | 800 | 0.0003 | 1.2422 |
|
64 |
-
| 0.0003 | 300.0 | 900 | 0.0003 | 1.2422 |
|
65 |
-
| 0.0003 | 333.33 | 1000 | 0.0003 | 1.2422 |
|
66 |
-
|
67 |
-
|
68 |
### Framework versions
|
69 |
|
70 |
- Transformers 4.38.0.dev0
|
|
|
6 |
tags:
|
7 |
- hf-asr-leaderboard
|
8 |
- generated_from_trainer
|
|
|
|
|
9 |
model-index:
|
10 |
- name: Whisper Base EN
|
11 |
results: []
|
|
|
17 |
# Whisper Base EN
|
18 |
|
19 |
This model is a fine-tuned version of [openai/whisper-base.en](https://huggingface.co/openai/whisper-base.en) on the ADLINK dataset.
|
|
|
|
|
|
|
20 |
|
21 |
## Model description
|
22 |
|
|
|
44 |
- lr_scheduler_warmup_steps: 500
|
45 |
- training_steps: 1000
|
46 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
47 |
### Framework versions
|
48 |
|
49 |
- Transformers 4.38.0.dev0
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 290401888
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d4dd5542fd6a1d35639e21384238f3bfe6c557c849d392b5905d33ee29e71db5
|
3 |
size 290401888
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4856
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:052d76957733079ab37d44bb73581927caad91ccc3e70a6414d53476f515966e
|
3 |
size 4856
|