Commit ·
ed0b2a7
1
Parent(s): dfda964
update model card README.md
Browse files
README.md
CHANGED
|
@@ -1,6 +1,7 @@
|
|
| 1 |
---
|
| 2 |
language:
|
| 3 |
-
-
|
|
|
|
| 4 |
tags:
|
| 5 |
- automatic-speech-recognition
|
| 6 |
- mozilla-foundation/common_voice_7_0
|
|
@@ -17,10 +18,10 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 17 |
|
| 18 |
#
|
| 19 |
|
| 20 |
-
This model is a fine-tuned version of [
|
| 21 |
It achieves the following results on the evaluation set:
|
| 22 |
-
- Loss:
|
| 23 |
-
- Wer: 1.
|
| 24 |
|
| 25 |
## Model description
|
| 26 |
|
|
@@ -39,21 +40,29 @@ More information needed
|
|
| 39 |
### Training hyperparameters
|
| 40 |
|
| 41 |
The following hyperparameters were used during training:
|
| 42 |
-
- learning_rate: 0.
|
| 43 |
-
- train_batch_size:
|
| 44 |
- eval_batch_size: 8
|
| 45 |
- seed: 42
|
|
|
|
|
|
|
| 46 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 47 |
- lr_scheduler_type: linear
|
|
|
|
| 48 |
- training_steps: 10
|
|
|
|
| 49 |
|
| 50 |
### Training results
|
| 51 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 52 |
|
| 53 |
|
| 54 |
### Framework versions
|
| 55 |
|
| 56 |
- Transformers 4.16.0.dev0
|
| 57 |
-
- Pytorch 1.10.1
|
| 58 |
- Datasets 1.17.1.dev0
|
| 59 |
- Tokenizers 0.11.0
|
|
|
|
| 1 |
---
|
| 2 |
language:
|
| 3 |
+
- sv-SE
|
| 4 |
+
license: apache-2.0
|
| 5 |
tags:
|
| 6 |
- automatic-speech-recognition
|
| 7 |
- mozilla-foundation/common_voice_7_0
|
|
|
|
| 18 |
|
| 19 |
#
|
| 20 |
|
| 21 |
+
This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on the MOZILLA-FOUNDATION/COMMON_VOICE_7_0 - SV-SE dataset.
|
| 22 |
It achieves the following results on the evaluation set:
|
| 23 |
+
- Loss: 14.2136
|
| 24 |
+
- Wer: 1.0
|
| 25 |
|
| 26 |
## Model description
|
| 27 |
|
|
|
|
| 40 |
### Training hyperparameters
|
| 41 |
|
| 42 |
The following hyperparameters were used during training:
|
| 43 |
+
- learning_rate: 0.0075
|
| 44 |
+
- train_batch_size: 8
|
| 45 |
- eval_batch_size: 8
|
| 46 |
- seed: 42
|
| 47 |
+
- gradient_accumulation_steps: 4
|
| 48 |
+
- total_train_batch_size: 32
|
| 49 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 50 |
- lr_scheduler_type: linear
|
| 51 |
+
- lr_scheduler_warmup_steps: 2000
|
| 52 |
- training_steps: 10
|
| 53 |
+
- mixed_precision_training: Native AMP
|
| 54 |
|
| 55 |
### Training results
|
| 56 |
|
| 57 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
| 58 |
+
|:-------------:|:-----:|:----:|:---------------:|:---:|
|
| 59 |
+
| 10.3458 | 0.01 | 5 | 15.0991 | 1.0 |
|
| 60 |
+
| 11.9029 | 0.03 | 10 | 14.2136 | 1.0 |
|
| 61 |
|
| 62 |
|
| 63 |
### Framework versions
|
| 64 |
|
| 65 |
- Transformers 4.16.0.dev0
|
| 66 |
+
- Pytorch 1.10.1+cu102
|
| 67 |
- Datasets 1.17.1.dev0
|
| 68 |
- Tokenizers 0.11.0
|