update model card README.md
Browse files
README.md
CHANGED
|
@@ -1,14 +1,27 @@
|
|
| 1 |
---
|
| 2 |
-
license:
|
| 3 |
tags:
|
| 4 |
-
- automatic-speech-recognition
|
| 5 |
-
- hts98/original_ver1.2
|
| 6 |
- generated_from_trainer
|
|
|
|
|
|
|
| 7 |
metrics:
|
| 8 |
- wer
|
| 9 |
model-index:
|
| 10 |
- name: wav2vec2-common_voice-tr-mms-demo
|
| 11 |
-
results:
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 12 |
---
|
| 13 |
|
| 14 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
@@ -16,9 +29,9 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 16 |
|
| 17 |
# wav2vec2-common_voice-tr-mms-demo
|
| 18 |
|
| 19 |
-
This model is a fine-tuned version of [
|
| 20 |
It achieves the following results on the evaluation set:
|
| 21 |
-
- Loss: 3.
|
| 22 |
- Wer: 1.0
|
| 23 |
|
| 24 |
## Model description
|
|
@@ -39,7 +52,7 @@ More information needed
|
|
| 39 |
|
| 40 |
The following hyperparameters were used during training:
|
| 41 |
- learning_rate: 0.001
|
| 42 |
-
- train_batch_size:
|
| 43 |
- eval_batch_size: 8
|
| 44 |
- seed: 42
|
| 45 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
|
@@ -51,16 +64,13 @@ The following hyperparameters were used during training:
|
|
| 51 |
|
| 52 |
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
| 53 |
|:-------------:|:-----:|:----:|:---------------:|:---:|
|
| 54 |
-
| No log | 1.
|
| 55 |
-
| No log |
|
| 56 |
-
| No log | 3.0 | 321 | 3.6340 | 1.0 |
|
| 57 |
-
| No log | 4.0 | 428 | 3.6451 | 1.0 |
|
| 58 |
-
| 3.9157 | 5.0 | 535 | 3.6482 | 1.0 |
|
| 59 |
|
| 60 |
|
| 61 |
### Framework versions
|
| 62 |
|
| 63 |
- Transformers 4.31.0.dev0
|
| 64 |
-
- Pytorch 2.0.
|
| 65 |
- Datasets 2.7.0
|
| 66 |
-
- Tokenizers 0.13.
|
|
|
|
| 1 |
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
tags:
|
|
|
|
|
|
|
| 4 |
- generated_from_trainer
|
| 5 |
+
datasets:
|
| 6 |
+
- common_voice
|
| 7 |
metrics:
|
| 8 |
- wer
|
| 9 |
model-index:
|
| 10 |
- name: wav2vec2-common_voice-tr-mms-demo
|
| 11 |
+
results:
|
| 12 |
+
- task:
|
| 13 |
+
name: Automatic Speech Recognition
|
| 14 |
+
type: automatic-speech-recognition
|
| 15 |
+
dataset:
|
| 16 |
+
name: common_voice
|
| 17 |
+
type: common_voice
|
| 18 |
+
config: vi
|
| 19 |
+
split: test
|
| 20 |
+
args: vi
|
| 21 |
+
metrics:
|
| 22 |
+
- name: Wer
|
| 23 |
+
type: wer
|
| 24 |
+
value: 1.0
|
| 25 |
---
|
| 26 |
|
| 27 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
|
| 29 |
|
| 30 |
# wav2vec2-common_voice-tr-mms-demo
|
| 31 |
|
| 32 |
+
This model is a fine-tuned version of [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) on the common_voice dataset.
|
| 33 |
It achieves the following results on the evaluation set:
|
| 34 |
+
- Loss: 3.6709
|
| 35 |
- Wer: 1.0
|
| 36 |
|
| 37 |
## Model description
|
|
|
|
| 52 |
|
| 53 |
The following hyperparameters were used during training:
|
| 54 |
- learning_rate: 0.001
|
| 55 |
+
- train_batch_size: 4
|
| 56 |
- eval_batch_size: 8
|
| 57 |
- seed: 42
|
| 58 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
|
|
|
| 64 |
|
| 65 |
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
| 66 |
|:-------------:|:-----:|:----:|:---------------:|:---:|
|
| 67 |
+
| No log | 1.79 | 100 | 3.6345 | 1.0 |
|
| 68 |
+
| No log | 3.57 | 200 | 3.6709 | 1.0 |
|
|
|
|
|
|
|
|
|
|
| 69 |
|
| 70 |
|
| 71 |
### Framework versions
|
| 72 |
|
| 73 |
- Transformers 4.31.0.dev0
|
| 74 |
+
- Pytorch 2.0.1+cu118
|
| 75 |
- Datasets 2.7.0
|
| 76 |
+
- Tokenizers 0.13.3
|