Commit
•
978c42d
1
Parent(s):
d22ba33
End of training
Browse files
README.md
ADDED
|
@@ -0,0 +1,62 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
base_model: Joshua-Abok/finetuning-wav2vec-large-swahili-asr-model_v10
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
datasets:
|
| 7 |
+
- common_voice_13_0
|
| 8 |
+
model-index:
|
| 9 |
+
- name: finetuning-wav2vec-lora-large-swahili-asr-model_v20
|
| 10 |
+
results: []
|
| 11 |
+
---
|
| 12 |
+
|
| 13 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 14 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 15 |
+
|
| 16 |
+
# finetuning-wav2vec-lora-large-swahili-asr-model_v20
|
| 17 |
+
|
| 18 |
+
This model is a fine-tuned version of [Joshua-Abok/finetuning-wav2vec-large-swahili-asr-model_v10](https://huggingface.co/Joshua-Abok/finetuning-wav2vec-large-swahili-asr-model_v10) on the common_voice_13_0 dataset.
|
| 19 |
+
It achieves the following results on the evaluation set:
|
| 20 |
+
- eval_loss: 0.3743
|
| 21 |
+
- eval_wer: 0.2301
|
| 22 |
+
- eval_runtime: 625.6728
|
| 23 |
+
- eval_samples_per_second: 18.014
|
| 24 |
+
- eval_steps_per_second: 2.252
|
| 25 |
+
- epoch: 1.94
|
| 26 |
+
- step: 2800
|
| 27 |
+
|
| 28 |
+
## Model description
|
| 29 |
+
|
| 30 |
+
More information needed
|
| 31 |
+
|
| 32 |
+
## Intended uses & limitations
|
| 33 |
+
|
| 34 |
+
More information needed
|
| 35 |
+
|
| 36 |
+
## Training and evaluation data
|
| 37 |
+
|
| 38 |
+
More information needed
|
| 39 |
+
|
| 40 |
+
## Training procedure
|
| 41 |
+
|
| 42 |
+
### Training hyperparameters
|
| 43 |
+
|
| 44 |
+
The following hyperparameters were used during training:
|
| 45 |
+
- learning_rate: 0.0003
|
| 46 |
+
- train_batch_size: 16
|
| 47 |
+
- eval_batch_size: 8
|
| 48 |
+
- seed: 42
|
| 49 |
+
- gradient_accumulation_steps: 2
|
| 50 |
+
- total_train_batch_size: 32
|
| 51 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 52 |
+
- lr_scheduler_type: linear
|
| 53 |
+
- lr_scheduler_warmup_steps: 500
|
| 54 |
+
- num_epochs: 30
|
| 55 |
+
- mixed_precision_training: Native AMP
|
| 56 |
+
|
| 57 |
+
### Framework versions
|
| 58 |
+
|
| 59 |
+
- Transformers 4.36.0.dev0
|
| 60 |
+
- Pytorch 2.0.1+cu118
|
| 61 |
+
- Datasets 2.14.7
|
| 62 |
+
- Tokenizers 0.15.0
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1261926332
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:75e120ced2f744491a7d4371c23e3e761d571243cd833e2efd0532d18904f138
|
| 3 |
size 1261926332
|
runs/Nov15_16-47-21_803aaecf50d2/events.out.tfevents.1700068396.803aaecf50d2.601.1
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:46bb647e42573a957444f484388f5c9d8c35c583e087cce643f59c5bf74e20e0
|
| 3 |
+
size 9153
|