Commit
•
4e65560
1
Parent(s):
a80758e
update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,78 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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-ia
|
| 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-ia
|
| 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: 0.1452
|
| 20 |
+
- Wer: 0.1253
|
| 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: 3e-05
|
| 40 |
+
- train_batch_size: 16
|
| 41 |
+
- eval_batch_size: 4
|
| 42 |
+
- seed: 42
|
| 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: linear
|
| 47 |
+
- lr_scheduler_warmup_steps: 400
|
| 48 |
+
- num_epochs: 30
|
| 49 |
+
- mixed_precision_training: Native AMP
|
| 50 |
+
|
| 51 |
+
### Training results
|
| 52 |
+
|
| 53 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
| 54 |
+
|:-------------:|:-----:|:----:|:---------------:|:------:|
|
| 55 |
+
| 7.432 | 1.87 | 400 | 2.9636 | 1.0 |
|
| 56 |
+
| 2.6922 | 3.74 | 800 | 2.2111 | 0.9977 |
|
| 57 |
+
| 1.2581 | 5.61 | 1200 | 0.4864 | 0.4028 |
|
| 58 |
+
| 0.6232 | 7.48 | 1600 | 0.2807 | 0.2413 |
|
| 59 |
+
| 0.4479 | 9.35 | 2000 | 0.2219 | 0.1885 |
|
| 60 |
+
| 0.3654 | 11.21 | 2400 | 0.1886 | 0.1606 |
|
| 61 |
+
| 0.323 | 13.08 | 2800 | 0.1716 | 0.1444 |
|
| 62 |
+
| 0.2935 | 14.95 | 3200 | 0.1687 | 0.1443 |
|
| 63 |
+
| 0.2707 | 16.82 | 3600 | 0.1632 | 0.1382 |
|
| 64 |
+
| 0.2559 | 18.69 | 4000 | 0.1507 | 0.1337 |
|
| 65 |
+
| 0.2433 | 20.56 | 4400 | 0.1572 | 0.1358 |
|
| 66 |
+
| 0.2338 | 22.43 | 4800 | 0.1489 | 0.1305 |
|
| 67 |
+
| 0.2258 | 24.3 | 5200 | 0.1485 | 0.1278 |
|
| 68 |
+
| 0.2218 | 26.17 | 5600 | 0.1470 | 0.1272 |
|
| 69 |
+
| 0.2169 | 28.04 | 6000 | 0.1470 | 0.1270 |
|
| 70 |
+
| 0.2117 | 29.91 | 6400 | 0.1452 | 0.1253 |
|
| 71 |
+
|
| 72 |
+
|
| 73 |
+
### Framework versions
|
| 74 |
+
|
| 75 |
+
- Transformers 4.17.0.dev0
|
| 76 |
+
- Pytorch 1.10.0+cu111
|
| 77 |
+
- Datasets 1.18.3
|
| 78 |
+
- Tokenizers 0.11.0
|