rebort
commited on
Commit
•
a586702
1
Parent(s):
4d518ac
End of training
Browse files- README.md +29 -8
- pytorch_model.bin +1 -1
README.md
CHANGED
|
@@ -4,10 +4,25 @@ base_model: facebook/wav2vec2-large-xlsr-53
|
|
| 4 |
tags:
|
| 5 |
- generated_from_trainer
|
| 6 |
datasets:
|
| 7 |
-
-
|
|
|
|
|
|
|
| 8 |
model-index:
|
| 9 |
- name: wav2vec2-large-xlsr-53-demo-colab
|
| 10 |
-
results:
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 11 |
---
|
| 12 |
|
| 13 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
@@ -15,7 +30,10 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 15 |
|
| 16 |
# wav2vec2-large-xlsr-53-demo-colab
|
| 17 |
|
| 18 |
-
This model is a fine-tuned version of [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) on the
|
|
|
|
|
|
|
|
|
|
| 19 |
|
| 20 |
## Model description
|
| 21 |
|
|
@@ -43,16 +61,19 @@ The following hyperparameters were used during training:
|
|
| 43 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 44 |
- lr_scheduler_type: linear
|
| 45 |
- lr_scheduler_warmup_steps: 500
|
| 46 |
-
- num_epochs:
|
| 47 |
-
- mixed_precision_training: Native AMP
|
| 48 |
|
| 49 |
### Training results
|
| 50 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 51 |
|
| 52 |
|
| 53 |
### Framework versions
|
| 54 |
|
| 55 |
-
- Transformers 4.
|
| 56 |
- Pytorch 2.1.0+cu118
|
| 57 |
-
- Datasets 2.
|
| 58 |
-
- Tokenizers 0.
|
|
|
|
| 4 |
tags:
|
| 5 |
- generated_from_trainer
|
| 6 |
datasets:
|
| 7 |
+
- common_voice_13_0
|
| 8 |
+
metrics:
|
| 9 |
+
- wer
|
| 10 |
model-index:
|
| 11 |
- name: wav2vec2-large-xlsr-53-demo-colab
|
| 12 |
+
results:
|
| 13 |
+
- task:
|
| 14 |
+
name: Automatic Speech Recognition
|
| 15 |
+
type: automatic-speech-recognition
|
| 16 |
+
dataset:
|
| 17 |
+
name: common_voice_13_0
|
| 18 |
+
type: common_voice_13_0
|
| 19 |
+
config: sah
|
| 20 |
+
split: test
|
| 21 |
+
args: sah
|
| 22 |
+
metrics:
|
| 23 |
+
- name: Wer
|
| 24 |
+
type: wer
|
| 25 |
+
value: 0.6214739858511686
|
| 26 |
---
|
| 27 |
|
| 28 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
|
| 30 |
|
| 31 |
# wav2vec2-large-xlsr-53-demo-colab
|
| 32 |
|
| 33 |
+
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_13_0 dataset.
|
| 34 |
+
It achieves the following results on the evaluation set:
|
| 35 |
+
- Loss: 0.6866
|
| 36 |
+
- Wer: 0.6215
|
| 37 |
|
| 38 |
## Model description
|
| 39 |
|
|
|
|
| 61 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 62 |
- lr_scheduler_type: linear
|
| 63 |
- lr_scheduler_warmup_steps: 500
|
| 64 |
+
- num_epochs: 30
|
|
|
|
| 65 |
|
| 66 |
### Training results
|
| 67 |
|
| 68 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
| 69 |
+
|:-------------:|:-----:|:----:|:---------------:|:------:|
|
| 70 |
+
| 5.0973 | 14.04 | 400 | 2.6074 | 1.0 |
|
| 71 |
+
| 0.6356 | 28.07 | 800 | 0.6866 | 0.6215 |
|
| 72 |
|
| 73 |
|
| 74 |
### Framework versions
|
| 75 |
|
| 76 |
+
- Transformers 4.34.0
|
| 77 |
- Pytorch 2.1.0+cu118
|
| 78 |
+
- Datasets 2.14.5
|
| 79 |
+
- Tokenizers 0.14.1
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1262107370
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:060e32f623ce84d578d6530146d2a71cc8aa95114698dec4f538139f18916d2c
|
| 3 |
size 1262107370
|