michaelszhu
commited on
Commit
•
bb66a12
1
Parent(s):
b3d8b23
End of training
Browse files- README.md +21 -16
- model.safetensors +1 -1
- training_args.bin +1 -1
README.md
CHANGED
@@ -23,7 +23,7 @@ model-index:
|
|
23 |
metrics:
|
24 |
- name: Wer
|
25 |
type: wer
|
26 |
-
value:
|
27 |
---
|
28 |
|
29 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
@@ -33,8 +33,8 @@ should probably proofread and complete it, then remove this comment. -->
|
|
33 |
|
34 |
This model is a fine-tuned version of [openai/wav2vec2](https://huggingface.co/openai/wav2vec2) on the Radio-Modified Common Voice 11.0 dataset.
|
35 |
It achieves the following results on the evaluation set:
|
36 |
-
- Loss:
|
37 |
-
- Wer:
|
38 |
|
39 |
## Model description
|
40 |
|
@@ -62,23 +62,28 @@ The following hyperparameters were used during training:
|
|
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:
|
66 |
- mixed_precision_training: Native AMP
|
67 |
|
68 |
### Training results
|
69 |
|
70 |
-
| Training Loss | Epoch
|
71 |
-
|
72 |
-
|
|
73 |
-
|
|
74 |
-
|
|
75 |
-
|
|
76 |
-
|
|
77 |
-
|
|
78 |
-
|
|
79 |
-
|
|
80 |
-
|
|
81 |
-
|
|
|
|
|
|
|
|
|
|
|
|
82 |
|
83 |
|
84 |
### Framework versions
|
|
|
23 |
metrics:
|
24 |
- name: Wer
|
25 |
type: wer
|
26 |
+
value: 95.72392751479289
|
27 |
---
|
28 |
|
29 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
33 |
|
34 |
This model is a fine-tuned version of [openai/wav2vec2](https://huggingface.co/openai/wav2vec2) on the Radio-Modified Common Voice 11.0 dataset.
|
35 |
It achieves the following results on the evaluation set:
|
36 |
+
- Loss: 316.8398
|
37 |
+
- Wer: 95.7239
|
38 |
|
39 |
## Model description
|
40 |
|
|
|
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: 15000
|
66 |
- mixed_precision_training: Native AMP
|
67 |
|
68 |
### Training results
|
69 |
|
70 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
71 |
+
|:-------------:|:-------:|:-----:|:---------------:|:-------:|
|
72 |
+
| 483.2584 | 2.0083 | 1000 | 434.6134 | 100.0 |
|
73 |
+
| 405.653 | 4.0167 | 2000 | 344.3590 | 96.6701 |
|
74 |
+
| 370.4857 | 6.025 | 3000 | 342.5145 | 99.8213 |
|
75 |
+
| 369.1107 | 9.0042 | 4000 | 327.9243 | 99.9830 |
|
76 |
+
| 346.2929 | 11.0125 | 5000 | 318.8220 | 99.3436 |
|
77 |
+
| 343.8343 | 13.0208 | 6000 | 312.6764 | 98.5592 |
|
78 |
+
| 341.4097 | 15.0292 | 7000 | 314.1781 | 99.1016 |
|
79 |
+
| 353.2187 | 18.0083 | 8000 | 337.7428 | 99.9430 |
|
80 |
+
| 362.3456 | 20.0167 | 9000 | 312.4731 | 97.1724 |
|
81 |
+
| 340.6648 | 22.025 | 10000 | 309.5160 | 96.7086 |
|
82 |
+
| 346.2773 | 25.0042 | 11000 | 307.8313 | 96.0953 |
|
83 |
+
| 324.1138 | 27.0125 | 12000 | 314.9616 | 95.1754 |
|
84 |
+
| 331.969 | 29.0208 | 13000 | 311.7163 | 95.5329 |
|
85 |
+
| 325.9136 | 31.0292 | 14000 | 315.2805 | 95.6577 |
|
86 |
+
| 335.0141 | 34.0083 | 15000 | 316.8398 | 95.7239 |
|
87 |
|
88 |
|
89 |
### Framework versions
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 377611120
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1194b44cf32232d854151864dd41924e4b88450c2c3a88059af6a38e8a82022b
|
3 |
size 377611120
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5048
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:04bc6ccbbfeda59b706be527b964fc6d2c17edb00ed471ee1cf8d3ceb403b100
|
3 |
size 5048
|