Model save
Browse files- README.md +76 -0
- model.safetensors +1 -1
README.md
ADDED
|
@@ -0,0 +1,76 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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-balanced
|
| 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-balanced
|
| 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: 0.3170
|
| 22 |
+
- Wer: 0.5544
|
| 23 |
+
- Cer: 0.1534
|
| 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: 4
|
| 47 |
+
- total_train_batch_size: 32
|
| 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 |
+
| 0.7567 | 0.2249 | 500 | 0.6175 | 0.7016 | 0.1984 |
|
| 59 |
+
| 0.5961 | 0.4498 | 1000 | 0.4316 | 0.6170 | 0.1722 |
|
| 60 |
+
| 0.4917 | 0.6748 | 1500 | 0.3739 | 0.6002 | 0.1658 |
|
| 61 |
+
| 0.4288 | 0.8997 | 2000 | 0.3521 | 0.5783 | 0.1614 |
|
| 62 |
+
| 0.4055 | 1.1246 | 2500 | 0.3367 | 0.5599 | 0.1549 |
|
| 63 |
+
| 0.406 | 1.3495 | 3000 | 0.3342 | 0.5581 | 0.1537 |
|
| 64 |
+
| 0.391 | 1.5744 | 3500 | 0.3183 | 0.5491 | 0.1518 |
|
| 65 |
+
| 0.3586 | 1.7994 | 4000 | 0.3144 | 0.5464 | 0.1515 |
|
| 66 |
+
| 0.3385 | 2.0243 | 4500 | 0.3167 | 0.5483 | 0.1518 |
|
| 67 |
+
| 0.3376 | 2.2492 | 5000 | 0.3200 | 0.5512 | 0.1525 |
|
| 68 |
+
| 0.3786 | 2.4741 | 5500 | 0.3170 | 0.5544 | 0.1534 |
|
| 69 |
+
|
| 70 |
+
|
| 71 |
+
### Framework versions
|
| 72 |
+
|
| 73 |
+
- Transformers 4.50.3
|
| 74 |
+
- Pytorch 2.7.0+cu126
|
| 75 |
+
- Datasets 3.5.0
|
| 76 |
+
- 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 sha256:97f502baff2fde4a27150b7b809047fa4565db7b38fa524fbd9d198cc6c560e4
|
| 3 |
size 1262037080
|