Commit
•
9b20aca
1
Parent(s):
dcaa0ef
End of training
Browse files- README.md +5 -4
- model.safetensors +1 -1
- preprocessor_config.json +1 -0
README.md
CHANGED
@@ -21,11 +21,12 @@ should probably proofread and complete it, then remove this comment. -->
|
|
21 |
[<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/projektarbeit_dalim/huggingface/runs/wobjnlgw)
|
22 |
[<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/projektarbeit_dalim/huggingface/runs/wobjnlgw)
|
23 |
[<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/projektarbeit_dalim/huggingface/runs/theziq77)
|
|
|
24 |
# 240801-wav2vec2-ASR-Global-All-Clients
|
25 |
|
26 |
This model is a fine-tuned version of [zainulhakim/240626-wav2vec2-ASR_Global](https://huggingface.co/zainulhakim/240626-wav2vec2-ASR_Global) on the None dataset.
|
27 |
It achieves the following results on the evaluation set:
|
28 |
-
- Loss: 3.
|
29 |
- Wer: 1.0
|
30 |
|
31 |
## Model description
|
@@ -59,9 +60,9 @@ The following hyperparameters were used during training:
|
|
59 |
|
60 |
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
61 |
|:-------------:|:------:|:----:|:---------------:|:---:|
|
62 |
-
| No log | 1.2658 | 100 | 3.
|
63 |
-
| No log | 2.5316 | 200 | 3.
|
64 |
-
| No log | 3.7975 | 300 | 3.
|
65 |
|
66 |
|
67 |
### Framework versions
|
|
|
21 |
[<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/projektarbeit_dalim/huggingface/runs/wobjnlgw)
|
22 |
[<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/projektarbeit_dalim/huggingface/runs/wobjnlgw)
|
23 |
[<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/projektarbeit_dalim/huggingface/runs/theziq77)
|
24 |
+
[<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/projektarbeit_dalim/huggingface/runs/s1l6rff5)
|
25 |
# 240801-wav2vec2-ASR-Global-All-Clients
|
26 |
|
27 |
This model is a fine-tuned version of [zainulhakim/240626-wav2vec2-ASR_Global](https://huggingface.co/zainulhakim/240626-wav2vec2-ASR_Global) on the None dataset.
|
28 |
It achieves the following results on the evaluation set:
|
29 |
+
- Loss: 3.0667
|
30 |
- Wer: 1.0
|
31 |
|
32 |
## Model description
|
|
|
60 |
|
61 |
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
62 |
|:-------------:|:------:|:----:|:---------------:|:---:|
|
63 |
+
| No log | 1.2658 | 100 | 3.0667 | 1.0 |
|
64 |
+
| No log | 2.5316 | 200 | 3.0889 | 1.0 |
|
65 |
+
| No log | 3.7975 | 300 | 3.1129 | 1.0 |
|
66 |
|
67 |
|
68 |
### 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 sha256:1a5483939d53028f54ab4c9fb41f4c998413d0f08c2150800ab710df1a144415
|
3 |
size 377611120
|
preprocessor_config.json
CHANGED
@@ -4,6 +4,7 @@
|
|
4 |
"feature_size": 1,
|
5 |
"padding_side": "right",
|
6 |
"padding_value": 0.0,
|
|
|
7 |
"return_attention_mask": false,
|
8 |
"sampling_rate": 16000
|
9 |
}
|
|
|
4 |
"feature_size": 1,
|
5 |
"padding_side": "right",
|
6 |
"padding_value": 0.0,
|
7 |
+
"processor_class": "Wav2Vec2Processor",
|
8 |
"return_attention_mask": false,
|
9 |
"sampling_rate": 16000
|
10 |
}
|