Model save
Browse files- README.md +79 -0
- model.safetensors +1 -1
README.md
ADDED
|
@@ -0,0 +1,79 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: transformers
|
| 3 |
+
license: apache-2.0
|
| 4 |
+
base_model: facebook/wav2vec2-xls-r-1b
|
| 5 |
+
tags:
|
| 6 |
+
- generated_from_trainer
|
| 7 |
+
metrics:
|
| 8 |
+
- wer
|
| 9 |
+
model-index:
|
| 10 |
+
- name: xls-r-1b-bigcgen-combined-15hrs-model
|
| 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 |
+
# xls-r-1b-bigcgen-combined-15hrs-model
|
| 18 |
+
|
| 19 |
+
This model is a fine-tuned version of [facebook/wav2vec2-xls-r-1b](https://huggingface.co/facebook/wav2vec2-xls-r-1b) on an unknown dataset.
|
| 20 |
+
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: 0.6606
|
| 22 |
+
- Wer: 0.7041
|
| 23 |
+
|
| 24 |
+
## Model description
|
| 25 |
+
|
| 26 |
+
More information needed
|
| 27 |
+
|
| 28 |
+
## Intended uses & limitations
|
| 29 |
+
|
| 30 |
+
More information needed
|
| 31 |
+
|
| 32 |
+
## Training and evaluation data
|
| 33 |
+
|
| 34 |
+
More information needed
|
| 35 |
+
|
| 36 |
+
## Training procedure
|
| 37 |
+
|
| 38 |
+
### Training hyperparameters
|
| 39 |
+
|
| 40 |
+
The following hyperparameters were used during training:
|
| 41 |
+
- learning_rate: 3e-05
|
| 42 |
+
- train_batch_size: 4
|
| 43 |
+
- eval_batch_size: 4
|
| 44 |
+
- seed: 42
|
| 45 |
+
- gradient_accumulation_steps: 2
|
| 46 |
+
- total_train_batch_size: 8
|
| 47 |
+
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 48 |
+
- lr_scheduler_type: linear
|
| 49 |
+
- lr_scheduler_warmup_steps: 500
|
| 50 |
+
- num_epochs: 30.0
|
| 51 |
+
|
| 52 |
+
### Training results
|
| 53 |
+
|
| 54 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
| 55 |
+
|:-------------:|:------:|:----:|:---------------:|:------:|
|
| 56 |
+
| No log | 0.1410 | 100 | 3.8893 | 1.0 |
|
| 57 |
+
| No log | 0.2821 | 200 | 2.6866 | 1.0 |
|
| 58 |
+
| No log | 0.4231 | 300 | 1.4204 | 1.0 |
|
| 59 |
+
| No log | 0.5642 | 400 | 0.8780 | 0.8847 |
|
| 60 |
+
| 5.5784 | 0.7052 | 500 | 0.8821 | 0.9583 |
|
| 61 |
+
| 5.5784 | 0.8463 | 600 | 0.6898 | 0.7509 |
|
| 62 |
+
| 5.5784 | 0.9873 | 700 | 0.6910 | 0.8690 |
|
| 63 |
+
| 5.5784 | 1.1283 | 800 | 0.6632 | 0.6810 |
|
| 64 |
+
| 5.5784 | 1.2694 | 900 | 0.6165 | 0.6048 |
|
| 65 |
+
| 1.2954 | 1.4104 | 1000 | 0.6006 | 0.6134 |
|
| 66 |
+
| 1.2954 | 1.5515 | 1100 | 0.6859 | 0.7684 |
|
| 67 |
+
| 1.2954 | 1.6925 | 1200 | 0.5857 | 0.6273 |
|
| 68 |
+
| 1.2954 | 1.8336 | 1300 | 0.6305 | 0.6155 |
|
| 69 |
+
| 1.2954 | 1.9746 | 1400 | 0.6213 | 0.5856 |
|
| 70 |
+
| 1.1582 | 2.1157 | 1500 | 0.5891 | 0.5984 |
|
| 71 |
+
| 1.1582 | 2.2567 | 1600 | 0.6606 | 0.7041 |
|
| 72 |
+
|
| 73 |
+
|
| 74 |
+
### Framework versions
|
| 75 |
+
|
| 76 |
+
- Transformers 4.47.1
|
| 77 |
+
- Pytorch 2.5.1+cu124
|
| 78 |
+
- Datasets 3.2.0
|
| 79 |
+
- Tokenizers 0.21.0
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 3850244720
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cb92a0847638d471b4130bee519f809d13335485347a2042d1cf329c3d338897
|
| 3 |
size 3850244720
|