Model save
Browse files- README.md +89 -0
- model.safetensors +1 -1
README.md
ADDED
|
@@ -0,0 +1,89 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: transformers
|
| 3 |
+
license: mit
|
| 4 |
+
base_model: facebook/w2v-bert-2.0
|
| 5 |
+
tags:
|
| 6 |
+
- generated_from_trainer
|
| 7 |
+
metrics:
|
| 8 |
+
- wer
|
| 9 |
+
model-index:
|
| 10 |
+
- name: w2v-bert-2.0-hausa_naijavoices_250h
|
| 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 |
+
# w2v-bert-2.0-hausa_naijavoices_250h
|
| 18 |
+
|
| 19 |
+
This model is a fine-tuned version of [facebook/w2v-bert-2.0](https://huggingface.co/facebook/w2v-bert-2.0) on an unknown dataset.
|
| 20 |
+
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: 0.2544
|
| 22 |
+
- Wer: 0.3309
|
| 23 |
+
- Cer: 0.1892
|
| 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: 3e-05
|
| 43 |
+
- train_batch_size: 160
|
| 44 |
+
- eval_batch_size: 160
|
| 45 |
+
- seed: 42
|
| 46 |
+
- distributed_type: multi-GPU
|
| 47 |
+
- num_devices: 2
|
| 48 |
+
- total_train_batch_size: 320
|
| 49 |
+
- total_eval_batch_size: 320
|
| 50 |
+
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 51 |
+
- lr_scheduler_type: linear
|
| 52 |
+
- lr_scheduler_warmup_ratio: 0.1
|
| 53 |
+
- num_epochs: 100.0
|
| 54 |
+
- mixed_precision_training: Native AMP
|
| 55 |
+
|
| 56 |
+
### Training results
|
| 57 |
+
|
| 58 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
|
| 59 |
+
|:-------------:|:-------:|:-----:|:---------------:|:------:|:------:|
|
| 60 |
+
| 0.3125 | 1.1173 | 1000 | 0.4133 | 0.4180 | 0.2128 |
|
| 61 |
+
| 0.2781 | 2.2346 | 2000 | 0.3208 | 0.3702 | 0.1998 |
|
| 62 |
+
| 0.2616 | 3.3520 | 3000 | 0.2858 | 0.3534 | 0.1950 |
|
| 63 |
+
| 0.2068 | 4.4693 | 4000 | 0.2772 | 0.3420 | 0.1923 |
|
| 64 |
+
| 0.3346 | 5.5866 | 5000 | 0.2620 | 0.3419 | 0.1915 |
|
| 65 |
+
| 0.2176 | 6.7039 | 6000 | 0.2535 | 0.3410 | 0.1916 |
|
| 66 |
+
| 0.1969 | 7.8212 | 7000 | 0.2466 | 0.3380 | 0.1909 |
|
| 67 |
+
| 0.1992 | 8.9385 | 8000 | 0.2467 | 0.3322 | 0.1896 |
|
| 68 |
+
| 0.197 | 10.0559 | 9000 | 0.2489 | 0.3322 | 0.1893 |
|
| 69 |
+
| 0.1832 | 11.1732 | 10000 | 0.2533 | 0.3385 | 0.1909 |
|
| 70 |
+
| 0.1859 | 12.2905 | 11000 | 0.2410 | 0.3334 | 0.1898 |
|
| 71 |
+
| 0.1751 | 13.4078 | 12000 | 0.2419 | 0.3307 | 0.1886 |
|
| 72 |
+
| 0.1569 | 14.5251 | 13000 | 0.2418 | 0.3321 | 0.1895 |
|
| 73 |
+
| 0.2345 | 15.6425 | 14000 | 0.2480 | 0.3352 | 0.1898 |
|
| 74 |
+
| 0.1769 | 16.7598 | 15000 | 0.2365 | 0.3280 | 0.1889 |
|
| 75 |
+
| 0.1634 | 17.8771 | 16000 | 0.2401 | 0.3345 | 0.1895 |
|
| 76 |
+
| 0.1647 | 18.9944 | 17000 | 0.2329 | 0.3303 | 0.1888 |
|
| 77 |
+
| 0.1937 | 20.1117 | 18000 | 0.2485 | 0.3273 | 0.1881 |
|
| 78 |
+
| 0.1671 | 21.2291 | 19000 | 0.2568 | 0.3327 | 0.1891 |
|
| 79 |
+
| 0.1229 | 22.3464 | 20000 | 0.2460 | 0.3304 | 0.1887 |
|
| 80 |
+
| 0.1252 | 23.4637 | 21000 | 0.2437 | 0.3337 | 0.1889 |
|
| 81 |
+
| 0.1186 | 24.5810 | 22000 | 0.2544 | 0.3309 | 0.1892 |
|
| 82 |
+
|
| 83 |
+
|
| 84 |
+
### Framework versions
|
| 85 |
+
|
| 86 |
+
- Transformers 4.48.1
|
| 87 |
+
- Pytorch 2.6.0+cu124
|
| 88 |
+
- Datasets 3.5.0
|
| 89 |
+
- 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 2423220460
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8a636265c21be1b7bcc09c049ae50bfdba3336c389e28bba3379ba367ee05e8f
|
| 3 |
size 2423220460
|