Commit
•
7a0be01
1
Parent(s):
f1ef9c3
End of training
Browse files- README.md +13 -13
- model.safetensors +1 -1
README.md
CHANGED
|
@@ -1,10 +1,10 @@
|
|
| 1 |
---
|
| 2 |
-
base_model: facebook/wav2vec2-xls-r-300m
|
| 3 |
license: apache-2.0
|
| 4 |
-
|
| 5 |
-
- wer
|
| 6 |
tags:
|
| 7 |
- generated_from_trainer
|
|
|
|
|
|
|
| 8 |
model-index:
|
| 9 |
- name: wav2vec2-large-xls-r-300m-lg-10hr-v4
|
| 10 |
results: []
|
|
@@ -13,14 +13,14 @@ model-index:
|
|
| 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/
|
| 17 |
# wav2vec2-large-xls-r-300m-lg-10hr-v4
|
| 18 |
|
| 19 |
This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on an unknown dataset.
|
| 20 |
It achieves the following results on the evaluation set:
|
| 21 |
-
- Loss:
|
| 22 |
- Wer: 1.0
|
| 23 |
-
- Cer:
|
| 24 |
|
| 25 |
## Model description
|
| 26 |
|
|
@@ -53,13 +53,13 @@ The following hyperparameters were used during training:
|
|
| 53 |
|
| 54 |
### Training results
|
| 55 |
|
| 56 |
-
| Training Loss | Epoch | Step | Validation Loss | Wer
|
| 57 |
-
|
| 58 |
-
| No log | 1.0 | 9 | 15.
|
| 59 |
-
| No log | 2.0 | 18 |
|
| 60 |
-
| No log | 3.0 | 27 | 14.
|
| 61 |
-
| No log | 4.0 | 36 | 14.
|
| 62 |
-
| No log | 5.0 | 45 | 13.
|
| 63 |
|
| 64 |
|
| 65 |
### 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-large-xls-r-300m-lg-10hr-v4
|
| 10 |
results: []
|
|
|
|
| 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/mfeyrsz7)
|
| 17 |
# wav2vec2-large-xls-r-300m-lg-10hr-v4
|
| 18 |
|
| 19 |
This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on an unknown dataset.
|
| 20 |
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: 19.7153
|
| 22 |
- Wer: 1.0
|
| 23 |
+
- Cer: 1.6348
|
| 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 | 9 | 15.1837 | 1.0 | 1.4446 |
|
| 59 |
+
| No log | 2.0 | 18 | 15.0587 | 1.0 | 1.4449 |
|
| 60 |
+
| No log | 3.0 | 27 | 14.7964 | 1.0 | 0.9425 |
|
| 61 |
+
| No log | 4.0 | 36 | 14.3556 | 1.0 | 0.9894 |
|
| 62 |
+
| No log | 5.0 | 45 | 13.7239 | 1.0 | 0.9992 |
|
| 63 |
|
| 64 |
|
| 65 |
### Framework versions
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1261934580
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ed6504bc6053b0bee7750ce76714ae5e007060e80905895ff4a114313f4f7535
|
| 3 |
size 1261934580
|