End of training
Browse files- README.md +22 -40
- model.safetensors +1 -1
README.md
CHANGED
@@ -1,41 +1,26 @@
|
|
1 |
---
|
2 |
-
base_model: facebook/wav2vec2-xls-r-300m
|
3 |
-
datasets:
|
4 |
-
- fleurs
|
5 |
license: apache-2.0
|
6 |
-
|
7 |
-
- wer
|
8 |
tags:
|
9 |
- generated_from_trainer
|
|
|
|
|
10 |
model-index:
|
11 |
- name: wav2vec2_xls_r_300m_FLEURS_Shona_1hr_v2
|
12 |
-
results:
|
13 |
-
- task:
|
14 |
-
type: automatic-speech-recognition
|
15 |
-
name: Automatic Speech Recognition
|
16 |
-
dataset:
|
17 |
-
name: fleurs
|
18 |
-
type: fleurs
|
19 |
-
config: sn_zw
|
20 |
-
split: validation
|
21 |
-
args: sn_zw
|
22 |
-
metrics:
|
23 |
-
- type: wer
|
24 |
-
value: 1.0053404539385848
|
25 |
-
name: Wer
|
26 |
---
|
27 |
|
28 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
29 |
should probably proofread and complete it, then remove this comment. -->
|
30 |
|
31 |
-
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/asr-africa-research-team/ASR%20Africa/runs/
|
32 |
# wav2vec2_xls_r_300m_FLEURS_Shona_1hr_v2
|
33 |
|
34 |
-
This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on the
|
35 |
It achieves the following results on the evaluation set:
|
36 |
-
- Loss:
|
37 |
-
- Wer: 1.
|
38 |
-
- Cer: 1.
|
39 |
|
40 |
## Model description
|
41 |
|
@@ -68,22 +53,19 @@ The following hyperparameters were used during training:
|
|
68 |
|
69 |
### Training results
|
70 |
|
71 |
-
| Training Loss | Epoch | Step | Validation Loss | Wer
|
72 |
-
|
73 |
-
| No log | 1.0 | 8 | 14.
|
74 |
-
| No log | 2.0 | 16 | 14.
|
75 |
-
| No log | 3.0 | 24 | 14.
|
76 |
-
| No log | 4.0 | 32 | 14.
|
77 |
-
| No log | 5.0 | 40 | 13.
|
78 |
-
| No log | 6.0 | 48 |
|
79 |
-
| No log | 7.0 | 56 |
|
80 |
-
| No log | 8.0 | 64 |
|
81 |
-
| No log | 9.0 | 72 |
|
82 |
-
| No log | 10.0 | 80 |
|
83 |
-
| No log | 11.0 | 88 |
|
84 |
-
| No log | 12.0 | 96 | 4.9727 | 1.0 | 1.0 |
|
85 |
-
| 10.6364 | 13.0 | 104 | 4.6466 | 1.0 | 1.0 |
|
86 |
-
| 10.6364 | 14.0 | 112 | 4.3706 | 1.0 | 1.0 |
|
87 |
|
88 |
|
89 |
### Framework versions
|
|
|
1 |
---
|
|
|
|
|
|
|
2 |
license: apache-2.0
|
3 |
+
base_model: facebook/wav2vec2-xls-r-300m
|
|
|
4 |
tags:
|
5 |
- generated_from_trainer
|
6 |
+
metrics:
|
7 |
+
- wer
|
8 |
model-index:
|
9 |
- name: wav2vec2_xls_r_300m_FLEURS_Shona_1hr_v2
|
10 |
+
results: []
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
11 |
---
|
12 |
|
13 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
14 |
should probably proofread and complete it, then remove this comment. -->
|
15 |
|
16 |
+
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/asr-africa-research-team/ASR%20Africa/runs/y5c5xv2u)
|
17 |
# wav2vec2_xls_r_300m_FLEURS_Shona_1hr_v2
|
18 |
|
19 |
+
This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on the None dataset.
|
20 |
It achieves the following results on the evaluation set:
|
21 |
+
- Loss: 14.3032
|
22 |
+
- Wer: 1.0
|
23 |
+
- Cer: 1.4684
|
24 |
|
25 |
## Model description
|
26 |
|
|
|
53 |
|
54 |
### Training results
|
55 |
|
56 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
|
57 |
+
|:-------------:|:-----:|:----:|:---------------:|:---:|:------:|
|
58 |
+
| No log | 1.0 | 8 | 14.7171 | 1.0 | 1.5610 |
|
59 |
+
| No log | 2.0 | 16 | 14.6350 | 1.0 | 1.1264 |
|
60 |
+
| No log | 3.0 | 24 | 14.4119 | 1.0 | 0.9462 |
|
61 |
+
| No log | 4.0 | 32 | 14.0495 | 1.0 | 0.9597 |
|
62 |
+
| No log | 5.0 | 40 | 13.4414 | 1.0 | 1.0 |
|
63 |
+
| No log | 6.0 | 48 | 12.1367 | 1.0 | 1.0 |
|
64 |
+
| No log | 7.0 | 56 | 9.9086 | 1.0 | 1.0 |
|
65 |
+
| No log | 8.0 | 64 | 7.8373 | 1.0 | 1.0 |
|
66 |
+
| No log | 9.0 | 72 | 6.3719 | 1.0 | 1.0 |
|
67 |
+
| No log | 10.0 | 80 | 5.4638 | 1.0 | 1.0 |
|
68 |
+
| No log | 11.0 | 88 | 4.8611 | 1.0 | 1.0 |
|
|
|
|
|
|
|
69 |
|
70 |
|
71 |
### Framework versions
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1261938680
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3f8e629c18bee7033adeaeb8b42a3bd91462d9fb0d34ec0f07da742c3264990e
|
3 |
size 1261938680
|