Commit
•
3478e6c
1
Parent(s):
5d50a79
End of training
Browse files- README.md +3 -1
- all_results.json +14 -0
- eval_results.json +9 -0
- train_results.json +8 -0
- trainer_state.json +0 -0
README.md
CHANGED
@@ -2,6 +2,8 @@
|
|
2 |
license: apache-2.0
|
3 |
base_model: facebook/hubert-large-ll60k
|
4 |
tags:
|
|
|
|
|
5 |
- generated_from_trainer
|
6 |
metrics:
|
7 |
- wer
|
@@ -15,7 +17,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
15 |
|
16 |
# hubert-large-ll60k-librispeech-multi-gpu
|
17 |
|
18 |
-
This model is a fine-tuned version of [facebook/hubert-large-ll60k](https://huggingface.co/facebook/hubert-large-ll60k) on
|
19 |
It achieves the following results on the evaluation set:
|
20 |
- Loss: 0.0616
|
21 |
- Wer: 0.0460
|
|
|
2 |
license: apache-2.0
|
3 |
base_model: facebook/hubert-large-ll60k
|
4 |
tags:
|
5 |
+
- automatic-speech-recognition
|
6 |
+
- macabdul9/librispeech-hubert-discrete-tokens
|
7 |
- generated_from_trainer
|
8 |
metrics:
|
9 |
- wer
|
|
|
17 |
|
18 |
# hubert-large-ll60k-librispeech-multi-gpu
|
19 |
|
20 |
+
This model is a fine-tuned version of [facebook/hubert-large-ll60k](https://huggingface.co/facebook/hubert-large-ll60k) on the MACABDUL9/LIBRISPEECH-HUBERT-DISCRETE-TOKENS - NA dataset.
|
21 |
It achieves the following results on the evaluation set:
|
22 |
- Loss: 0.0616
|
23 |
- Wer: 0.0460
|
all_results.json
ADDED
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 4.0,
|
3 |
+
"eval_loss": 0.06156753748655319,
|
4 |
+
"eval_runtime": 183.6191,
|
5 |
+
"eval_samples": 2642,
|
6 |
+
"eval_samples_per_second": 14.388,
|
7 |
+
"eval_steps_per_second": 0.452,
|
8 |
+
"eval_wer": 0.04597381991273304,
|
9 |
+
"train_loss": 0.13451409900581351,
|
10 |
+
"train_runtime": 46616.5397,
|
11 |
+
"train_samples": 28538,
|
12 |
+
"train_samples_per_second": 2.449,
|
13 |
+
"train_steps_per_second": 0.306
|
14 |
+
}
|
eval_results.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 4.0,
|
3 |
+
"eval_loss": 0.06156753748655319,
|
4 |
+
"eval_runtime": 183.6191,
|
5 |
+
"eval_samples": 2642,
|
6 |
+
"eval_samples_per_second": 14.388,
|
7 |
+
"eval_steps_per_second": 0.452,
|
8 |
+
"eval_wer": 0.04597381991273304
|
9 |
+
}
|
train_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 4.0,
|
3 |
+
"train_loss": 0.13451409900581351,
|
4 |
+
"train_runtime": 46616.5397,
|
5 |
+
"train_samples": 28538,
|
6 |
+
"train_samples_per_second": 2.449,
|
7 |
+
"train_steps_per_second": 0.306
|
8 |
+
}
|
trainer_state.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|