Model save
Browse files- README.md +78 -0
- model.safetensors +1 -1
README.md
ADDED
|
@@ -0,0 +1,78 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: transformers
|
| 3 |
+
license: apache-2.0
|
| 4 |
+
base_model: facebook/wav2vec2-xls-r-300m
|
| 5 |
+
tags:
|
| 6 |
+
- generated_from_trainer
|
| 7 |
+
metrics:
|
| 8 |
+
- wer
|
| 9 |
+
model-index:
|
| 10 |
+
- name: Wav2vec2-fula-no0
|
| 11 |
+
results: []
|
| 12 |
+
---
|
| 13 |
+
|
| 14 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 15 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 16 |
+
|
| 17 |
+
# Wav2vec2-fula-no0
|
| 18 |
+
|
| 19 |
+
This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on an unknown dataset.
|
| 20 |
+
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: 0.4417
|
| 22 |
+
- Wer: 0.5500
|
| 23 |
+
- Cer: 0.1528
|
| 24 |
+
|
| 25 |
+
## Model description
|
| 26 |
+
|
| 27 |
+
More information needed
|
| 28 |
+
|
| 29 |
+
## Intended uses & limitations
|
| 30 |
+
|
| 31 |
+
More information needed
|
| 32 |
+
|
| 33 |
+
## Training and evaluation data
|
| 34 |
+
|
| 35 |
+
More information needed
|
| 36 |
+
|
| 37 |
+
## Training procedure
|
| 38 |
+
|
| 39 |
+
### Training hyperparameters
|
| 40 |
+
|
| 41 |
+
The following hyperparameters were used during training:
|
| 42 |
+
- learning_rate: 0.0003
|
| 43 |
+
- train_batch_size: 8
|
| 44 |
+
- eval_batch_size: 8
|
| 45 |
+
- seed: 42
|
| 46 |
+
- gradient_accumulation_steps: 2
|
| 47 |
+
- total_train_batch_size: 16
|
| 48 |
+
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 49 |
+
- lr_scheduler_type: linear
|
| 50 |
+
- lr_scheduler_warmup_steps: 1000
|
| 51 |
+
- num_epochs: 60.0
|
| 52 |
+
- mixed_precision_training: Native AMP
|
| 53 |
+
|
| 54 |
+
### Training results
|
| 55 |
+
|
| 56 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
|
| 57 |
+
|:-------------:|:------:|:----:|:---------------:|:------:|:------:|
|
| 58 |
+
| 0.5615 | 0.1970 | 500 | 0.6706 | 0.7329 | 0.2082 |
|
| 59 |
+
| 0.3606 | 0.3939 | 1000 | 0.5461 | 0.6352 | 0.1786 |
|
| 60 |
+
| 0.3103 | 0.5909 | 1500 | 0.4960 | 0.6026 | 0.1695 |
|
| 61 |
+
| 0.228 | 0.7879 | 2000 | 0.5087 | 0.5917 | 0.1635 |
|
| 62 |
+
| 0.2502 | 0.9848 | 2500 | 0.4720 | 0.5835 | 0.1648 |
|
| 63 |
+
| 0.2841 | 1.1816 | 3000 | 0.4652 | 0.6019 | 0.1701 |
|
| 64 |
+
| 0.2603 | 1.3786 | 3500 | 0.4726 | 0.5685 | 0.1588 |
|
| 65 |
+
| 0.2538 | 1.5755 | 4000 | 0.4538 | 0.5667 | 0.1573 |
|
| 66 |
+
| 0.2215 | 1.7725 | 4500 | 0.4649 | 0.5615 | 0.1581 |
|
| 67 |
+
| 0.2329 | 1.9695 | 5000 | 0.4407 | 0.5583 | 0.1549 |
|
| 68 |
+
| 0.2111 | 2.1662 | 5500 | 0.4677 | 0.5529 | 0.1542 |
|
| 69 |
+
| 0.2018 | 2.3632 | 6000 | 0.4574 | 0.5507 | 0.1531 |
|
| 70 |
+
| 0.2421 | 2.5602 | 6500 | 0.4417 | 0.5500 | 0.1528 |
|
| 71 |
+
|
| 72 |
+
|
| 73 |
+
### Framework versions
|
| 74 |
+
|
| 75 |
+
- Transformers 4.50.3
|
| 76 |
+
- Pytorch 2.7.0+cu126
|
| 77 |
+
- Datasets 3.5.0
|
| 78 |
+
- Tokenizers 0.21.1
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1262037080
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2ac816304300b287d24435424f95612d69ccccc6143500b7fb708dd7adb04611
|
| 3 |
size 1262037080
|