End of training
Browse files- README.md +25 -30
- adapter.tam-256.safetensors +1 -1
- model.safetensors +1 -1
README.md
CHANGED
@@ -1,20 +1,20 @@
|
|
1 |
---
|
|
|
|
|
2 |
base_model: facebook/mms-1b-all
|
|
|
|
|
3 |
datasets:
|
4 |
- common_voice_17_0
|
5 |
-
library_name: transformers
|
6 |
-
license: cc-by-nc-4.0
|
7 |
metrics:
|
8 |
- wer
|
9 |
- bleu
|
10 |
-
tags:
|
11 |
-
- generated_from_trainer
|
12 |
model-index:
|
13 |
- name: wav2vec2-mms-1b-CV17.0-training_set_variations
|
14 |
results:
|
15 |
- task:
|
16 |
-
type: automatic-speech-recognition
|
17 |
name: Automatic Speech Recognition
|
|
|
18 |
dataset:
|
19 |
name: common_voice_17_0
|
20 |
type: common_voice_17_0
|
@@ -22,12 +22,12 @@ model-index:
|
|
22 |
split: validation
|
23 |
args: ta
|
24 |
metrics:
|
25 |
-
-
|
26 |
-
|
27 |
-
|
28 |
-
-
|
29 |
-
|
30 |
-
|
31 |
---
|
32 |
|
33 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
@@ -37,10 +37,10 @@ should probably proofread and complete it, then remove this comment. -->
|
|
37 |
|
38 |
This model is a fine-tuned version of [facebook/mms-1b-all](https://huggingface.co/facebook/mms-1b-all) on the common_voice_17_0 dataset.
|
39 |
It achieves the following results on the evaluation set:
|
40 |
-
- Loss: 0.
|
41 |
-
- Wer: 0.
|
42 |
-
- Cer: 0.
|
43 |
-
- Bleu: 0.
|
44 |
|
45 |
## Model description
|
46 |
|
@@ -73,21 +73,16 @@ The following hyperparameters were used during training:
|
|
73 |
|
74 |
### Training results
|
75 |
|
76 |
-
| Training Loss | Epoch
|
77 |
-
|
78 |
-
| 11.
|
79 |
-
| 1.
|
80 |
-
| 0.
|
81 |
-
| 0.
|
82 |
-
| 0.
|
83 |
-
| 0.
|
84 |
-
| 0.
|
85 |
-
| 0.
|
86 |
-
| 0.0952 | 28.125 | 450 | 0.2828 | 0.4139 | 0.0691 | 0.3605 |
|
87 |
-
| 0.0919 | 31.25 | 500 | 0.2972 | 0.4283 | 0.0721 | 0.3355 |
|
88 |
-
| 0.0909 | 34.375 | 550 | 0.2971 | 0.4155 | 0.0686 | 0.3567 |
|
89 |
-
| 0.0744 | 37.5 | 600 | 0.3086 | 0.4241 | 0.0705 | 0.3461 |
|
90 |
-
| 0.069 | 40.625 | 650 | 0.3166 | 0.4166 | 0.0689 | 0.3603 |
|
91 |
|
92 |
|
93 |
### Framework versions
|
|
|
1 |
---
|
2 |
+
library_name: transformers
|
3 |
+
license: cc-by-nc-4.0
|
4 |
base_model: facebook/mms-1b-all
|
5 |
+
tags:
|
6 |
+
- generated_from_trainer
|
7 |
datasets:
|
8 |
- common_voice_17_0
|
|
|
|
|
9 |
metrics:
|
10 |
- wer
|
11 |
- bleu
|
|
|
|
|
12 |
model-index:
|
13 |
- name: wav2vec2-mms-1b-CV17.0-training_set_variations
|
14 |
results:
|
15 |
- task:
|
|
|
16 |
name: Automatic Speech Recognition
|
17 |
+
type: automatic-speech-recognition
|
18 |
dataset:
|
19 |
name: common_voice_17_0
|
20 |
type: common_voice_17_0
|
|
|
22 |
split: validation
|
23 |
args: ta
|
24 |
metrics:
|
25 |
+
- name: Wer
|
26 |
+
type: wer
|
27 |
+
value: 0.4250355227574827
|
28 |
+
- name: Bleu
|
29 |
+
type: bleu
|
30 |
+
value: 0.3461897882903843
|
31 |
---
|
32 |
|
33 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
37 |
|
38 |
This model is a fine-tuned version of [facebook/mms-1b-all](https://huggingface.co/facebook/mms-1b-all) on the common_voice_17_0 dataset.
|
39 |
It achieves the following results on the evaluation set:
|
40 |
+
- Loss: 0.3320
|
41 |
+
- Wer: 0.4250
|
42 |
+
- Cer: 0.0720
|
43 |
+
- Bleu: 0.3462
|
44 |
|
45 |
## Model description
|
46 |
|
|
|
73 |
|
74 |
### Training results
|
75 |
|
76 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer | Cer | Bleu |
|
77 |
+
|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|
|
78 |
+
| 11.5156 | 6.25 | 50 | 5.5076 | 1.0 | 0.9701 | 0.0 |
|
79 |
+
| 1.8133 | 12.5 | 100 | 0.2759 | 0.4067 | 0.0674 | 0.3610 |
|
80 |
+
| 0.1751 | 18.75 | 150 | 0.2414 | 0.3828 | 0.0639 | 0.3924 |
|
81 |
+
| 0.1315 | 25.0 | 200 | 0.2556 | 0.3887 | 0.0649 | 0.3901 |
|
82 |
+
| 0.1 | 31.25 | 250 | 0.2842 | 0.4168 | 0.0700 | 0.3520 |
|
83 |
+
| 0.0842 | 37.5 | 300 | 0.2997 | 0.4133 | 0.0699 | 0.3571 |
|
84 |
+
| 0.0717 | 43.75 | 350 | 0.3210 | 0.4260 | 0.0732 | 0.3431 |
|
85 |
+
| 0.0608 | 50.0 | 400 | 0.3320 | 0.4250 | 0.0720 | 0.3462 |
|
|
|
|
|
|
|
|
|
|
|
86 |
|
87 |
|
88 |
### Framework versions
|
adapter.tam-256.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 8926640
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:58a4c631a4a4f3e0dd32ec6ffdcdea8cf9bb4585c9ac9a7702796db9f2a2406c
|
3 |
size 8926640
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 3859019024
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:81a18655b2c0b5bbdfaf12993f18aa6e4342dced967e1760b5dd9e277aaf298c
|
3 |
size 3859019024
|