Model save
Browse files- README.md +25 -17
- model.safetensors +1 -1
README.md
CHANGED
|
@@ -3,8 +3,6 @@ library_name: transformers
|
|
| 3 |
license: apache-2.0
|
| 4 |
base_model: facebook/wav2vec2-xls-r-1b
|
| 5 |
tags:
|
| 6 |
-
- automatic-speech-recognition
|
| 7 |
-
- natbed
|
| 8 |
- generated_from_trainer
|
| 9 |
metrics:
|
| 10 |
- wer
|
|
@@ -18,10 +16,10 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 18 |
|
| 19 |
# xls-r-1b-bem-natbed-combined-model
|
| 20 |
|
| 21 |
-
This model is a fine-tuned version of [facebook/wav2vec2-xls-r-1b](https://huggingface.co/facebook/wav2vec2-xls-r-1b) on
|
| 22 |
It achieves the following results on the evaluation set:
|
| 23 |
-
- Loss: 0.
|
| 24 |
-
- Wer: 0.
|
| 25 |
|
| 26 |
## Model description
|
| 27 |
|
|
@@ -40,7 +38,7 @@ More information needed
|
|
| 40 |
### Training hyperparameters
|
| 41 |
|
| 42 |
The following hyperparameters were used during training:
|
| 43 |
-
- learning_rate:
|
| 44 |
- train_batch_size: 8
|
| 45 |
- eval_batch_size: 8
|
| 46 |
- seed: 42
|
|
@@ -56,17 +54,27 @@ The following hyperparameters were used during training:
|
|
| 56 |
|
| 57 |
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
| 58 |
|:-------------:|:------:|:----:|:---------------:|:------:|
|
| 59 |
-
|
|
| 60 |
-
|
|
| 61 |
-
| 1.
|
| 62 |
-
| 0.
|
| 63 |
-
| 0.
|
| 64 |
-
| 0.
|
| 65 |
-
| 0.
|
| 66 |
-
| 0.
|
| 67 |
-
| 0.
|
| 68 |
-
| 0.
|
| 69 |
-
| 0.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 70 |
|
| 71 |
|
| 72 |
### Framework versions
|
|
|
|
| 3 |
license: apache-2.0
|
| 4 |
base_model: facebook/wav2vec2-xls-r-1b
|
| 5 |
tags:
|
|
|
|
|
|
|
| 6 |
- generated_from_trainer
|
| 7 |
metrics:
|
| 8 |
- wer
|
|
|
|
| 16 |
|
| 17 |
# xls-r-1b-bem-natbed-combined-model
|
| 18 |
|
| 19 |
+
This model is a fine-tuned version of [facebook/wav2vec2-xls-r-1b](https://huggingface.co/facebook/wav2vec2-xls-r-1b) on an unknown dataset.
|
| 20 |
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: 0.7032
|
| 22 |
+
- Wer: 0.7424
|
| 23 |
|
| 24 |
## Model description
|
| 25 |
|
|
|
|
| 38 |
### Training hyperparameters
|
| 39 |
|
| 40 |
The following hyperparameters were used during training:
|
| 41 |
+
- learning_rate: 0.0003
|
| 42 |
- train_batch_size: 8
|
| 43 |
- eval_batch_size: 8
|
| 44 |
- seed: 42
|
|
|
|
| 54 |
|
| 55 |
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
| 56 |
|:-------------:|:------:|:----:|:---------------:|:------:|
|
| 57 |
+
| 5.0296 | 0.2503 | 100 | 2.8071 | 1.0 |
|
| 58 |
+
| 1.5792 | 0.5006 | 200 | 1.1184 | 0.9645 |
|
| 59 |
+
| 1.1422 | 0.7509 | 300 | 1.0389 | 0.9606 |
|
| 60 |
+
| 0.9883 | 1.0013 | 400 | 1.0494 | 0.9989 |
|
| 61 |
+
| 0.8999 | 1.2516 | 500 | 0.8692 | 0.8683 |
|
| 62 |
+
| 0.9135 | 1.5019 | 600 | 0.8564 | 0.8430 |
|
| 63 |
+
| 0.8898 | 1.7522 | 700 | 0.8451 | 0.8522 |
|
| 64 |
+
| 0.9089 | 2.0025 | 800 | 0.8857 | 0.8485 |
|
| 65 |
+
| 0.8292 | 2.2528 | 900 | 0.8662 | 0.8580 |
|
| 66 |
+
| 0.7921 | 2.5031 | 1000 | 0.7964 | 0.7969 |
|
| 67 |
+
| 0.7983 | 2.7534 | 1100 | 0.7896 | 0.7951 |
|
| 68 |
+
| 0.7946 | 3.0038 | 1200 | 0.7667 | 0.7947 |
|
| 69 |
+
| 0.7488 | 3.2541 | 1300 | 0.8180 | 0.8495 |
|
| 70 |
+
| 0.7428 | 3.5044 | 1400 | 0.7548 | 0.7688 |
|
| 71 |
+
| 0.7256 | 3.7547 | 1500 | 0.7258 | 0.7596 |
|
| 72 |
+
| 0.741 | 4.0050 | 1600 | 0.7665 | 0.7718 |
|
| 73 |
+
| 0.6775 | 4.2553 | 1700 | 0.7922 | 0.7775 |
|
| 74 |
+
| 0.6795 | 4.5056 | 1800 | 0.7026 | 0.7512 |
|
| 75 |
+
| 0.683 | 4.7559 | 1900 | 0.7051 | 0.7225 |
|
| 76 |
+
| 0.6838 | 5.0063 | 2000 | 0.7196 | 0.7503 |
|
| 77 |
+
| 0.6005 | 5.2566 | 2100 | 0.7032 | 0.7424 |
|
| 78 |
|
| 79 |
|
| 80 |
### Framework versions
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 3850326704
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2370c583f61ff21c6e76106b27afcdcaa7f830c8615f454d73d22029341bce0a
|
| 3 |
size 3850326704
|