Commit
•
5fe39c2
1
Parent(s):
83474f1
End of training
Browse files- README.md +87 -0
- model.safetensors +1 -1
README.md
ADDED
|
@@ -0,0 +1,87 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
base_model: facebook/wav2vec2-xls-r-300m
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
datasets:
|
| 7 |
+
- common_voice_17_0
|
| 8 |
+
metrics:
|
| 9 |
+
- wer
|
| 10 |
+
model-index:
|
| 11 |
+
- name: results
|
| 12 |
+
results:
|
| 13 |
+
- task:
|
| 14 |
+
name: Automatic Speech Recognition
|
| 15 |
+
type: automatic-speech-recognition
|
| 16 |
+
dataset:
|
| 17 |
+
name: common_voice_17_0
|
| 18 |
+
type: common_voice_17_0
|
| 19 |
+
config: ne-NP
|
| 20 |
+
split: validated+other
|
| 21 |
+
args: ne-NP
|
| 22 |
+
metrics:
|
| 23 |
+
- name: Wer
|
| 24 |
+
type: wer
|
| 25 |
+
value: 0.5865921787709497
|
| 26 |
+
---
|
| 27 |
+
|
| 28 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 29 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 30 |
+
|
| 31 |
+
# results
|
| 32 |
+
|
| 33 |
+
This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on the common_voice_17_0 dataset.
|
| 34 |
+
It achieves the following results on the evaluation set:
|
| 35 |
+
- Loss: 0.7289
|
| 36 |
+
- Wer: 0.5866
|
| 37 |
+
|
| 38 |
+
## Model description
|
| 39 |
+
|
| 40 |
+
More information needed
|
| 41 |
+
|
| 42 |
+
## Intended uses & limitations
|
| 43 |
+
|
| 44 |
+
More information needed
|
| 45 |
+
|
| 46 |
+
## Training and evaluation data
|
| 47 |
+
|
| 48 |
+
More information needed
|
| 49 |
+
|
| 50 |
+
## Training procedure
|
| 51 |
+
|
| 52 |
+
### Training hyperparameters
|
| 53 |
+
|
| 54 |
+
The following hyperparameters were used during training:
|
| 55 |
+
- learning_rate: 0.0003
|
| 56 |
+
- train_batch_size: 16
|
| 57 |
+
- eval_batch_size: 8
|
| 58 |
+
- seed: 42
|
| 59 |
+
- gradient_accumulation_steps: 2
|
| 60 |
+
- total_train_batch_size: 32
|
| 61 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 62 |
+
- lr_scheduler_type: linear
|
| 63 |
+
- lr_scheduler_warmup_steps: 200
|
| 64 |
+
- num_epochs: 30
|
| 65 |
+
- mixed_precision_training: Native AMP
|
| 66 |
+
|
| 67 |
+
### Training results
|
| 68 |
+
|
| 69 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
| 70 |
+
|:-------------:|:-------:|:----:|:---------------:|:------:|
|
| 71 |
+
| 1.4919 | 2.9851 | 100 | 1.2236 | 0.9106 |
|
| 72 |
+
| 1.0086 | 5.9701 | 200 | 0.9436 | 0.8291 |
|
| 73 |
+
| 0.6072 | 8.9552 | 300 | 0.8277 | 0.7117 |
|
| 74 |
+
| 0.55 | 11.9403 | 400 | 0.7774 | 0.6726 |
|
| 75 |
+
| 0.3398 | 14.9254 | 500 | 0.7344 | 0.6212 |
|
| 76 |
+
| 0.2543 | 17.9104 | 600 | 0.7368 | 0.6212 |
|
| 77 |
+
| 0.3558 | 20.8955 | 700 | 0.7313 | 0.5788 |
|
| 78 |
+
| 0.1751 | 23.8806 | 800 | 0.7060 | 0.5855 |
|
| 79 |
+
| 0.1502 | 26.8657 | 900 | 0.7289 | 0.5866 |
|
| 80 |
+
|
| 81 |
+
|
| 82 |
+
### Framework versions
|
| 83 |
+
|
| 84 |
+
- Transformers 4.41.2
|
| 85 |
+
- Pytorch 2.3.0+cu121
|
| 86 |
+
- Datasets 2.20.0
|
| 87 |
+
- Tokenizers 0.19.1
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1262078080
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fad9d84edae3c7401eebbb747f41f995e066a205e9dda9df2a2c8759599d8094
|
| 3 |
size 1262078080
|