Commit
•
19dfbde
1
Parent(s):
b10ee1b
update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,76 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
datasets:
|
| 6 |
+
- common_voice
|
| 7 |
+
model-index:
|
| 8 |
+
- name: wav2vec2-large-xls-r-300m-ha-cv8
|
| 9 |
+
results: []
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 13 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 14 |
+
|
| 15 |
+
# wav2vec2-large-xls-r-300m-ha-cv8
|
| 16 |
+
|
| 17 |
+
This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on the common_voice dataset.
|
| 18 |
+
It achieves the following results on the evaluation set:
|
| 19 |
+
- Loss: 0.6094
|
| 20 |
+
- Wer: 0.5234
|
| 21 |
+
|
| 22 |
+
## Model description
|
| 23 |
+
|
| 24 |
+
More information needed
|
| 25 |
+
|
| 26 |
+
## Intended uses & limitations
|
| 27 |
+
|
| 28 |
+
More information needed
|
| 29 |
+
|
| 30 |
+
## Training and evaluation data
|
| 31 |
+
|
| 32 |
+
More information needed
|
| 33 |
+
|
| 34 |
+
## Training procedure
|
| 35 |
+
|
| 36 |
+
### Training hyperparameters
|
| 37 |
+
|
| 38 |
+
The following hyperparameters were used during training:
|
| 39 |
+
- learning_rate: 0.0001
|
| 40 |
+
- train_batch_size: 16
|
| 41 |
+
- eval_batch_size: 8
|
| 42 |
+
- seed: 13
|
| 43 |
+
- gradient_accumulation_steps: 2
|
| 44 |
+
- total_train_batch_size: 32
|
| 45 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 46 |
+
- lr_scheduler_type: cosine_with_restarts
|
| 47 |
+
- lr_scheduler_warmup_steps: 1000
|
| 48 |
+
- num_epochs: 100
|
| 49 |
+
|
| 50 |
+
### Training results
|
| 51 |
+
|
| 52 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
| 53 |
+
|:-------------:|:-----:|:----:|:---------------:|:------:|
|
| 54 |
+
| 2.9599 | 6.56 | 400 | 2.8650 | 1.0 |
|
| 55 |
+
| 2.7357 | 13.11 | 800 | 2.7377 | 0.9951 |
|
| 56 |
+
| 1.3012 | 19.67 | 1200 | 0.6686 | 0.7111 |
|
| 57 |
+
| 1.0454 | 26.23 | 1600 | 0.5686 | 0.6137 |
|
| 58 |
+
| 0.9069 | 32.79 | 2000 | 0.5576 | 0.5815 |
|
| 59 |
+
| 0.82 | 39.34 | 2400 | 0.5502 | 0.5591 |
|
| 60 |
+
| 0.7413 | 45.9 | 2800 | 0.5970 | 0.5586 |
|
| 61 |
+
| 0.6872 | 52.46 | 3200 | 0.5817 | 0.5428 |
|
| 62 |
+
| 0.634 | 59.02 | 3600 | 0.5636 | 0.5314 |
|
| 63 |
+
| 0.6022 | 65.57 | 4000 | 0.5780 | 0.5229 |
|
| 64 |
+
| 0.5705 | 72.13 | 4400 | 0.6036 | 0.5323 |
|
| 65 |
+
| 0.5408 | 78.69 | 4800 | 0.6119 | 0.5336 |
|
| 66 |
+
| 0.5225 | 85.25 | 5200 | 0.6105 | 0.5270 |
|
| 67 |
+
| 0.5265 | 91.8 | 5600 | 0.6034 | 0.5231 |
|
| 68 |
+
| 0.5154 | 98.36 | 6000 | 0.6094 | 0.5234 |
|
| 69 |
+
|
| 70 |
+
|
| 71 |
+
### Framework versions
|
| 72 |
+
|
| 73 |
+
- Transformers 4.16.1
|
| 74 |
+
- Pytorch 1.10.0+cu111
|
| 75 |
+
- Datasets 1.18.2
|
| 76 |
+
- Tokenizers 0.11.0
|