Model save
Browse files- README.md +29 -3
- model.safetensors +1 -1
README.md
CHANGED
|
@@ -1,13 +1,28 @@
|
|
| 1 |
---
|
| 2 |
license: apache-2.0
|
|
|
|
| 3 |
tags:
|
| 4 |
- generated_from_trainer
|
| 5 |
-
base_model: Amadkour/wav2vec2-large-xls-r-300m-tr-softkour
|
| 6 |
datasets:
|
| 7 |
- common_voice_11_0
|
|
|
|
|
|
|
| 8 |
model-index:
|
| 9 |
- name: wav2vec2-large-xls-r-300m-tr-softkour
|
| 10 |
-
results:
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 11 |
---
|
| 12 |
|
| 13 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
@@ -16,6 +31,9 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 16 |
# wav2vec2-large-xls-r-300m-tr-softkour
|
| 17 |
|
| 18 |
This model is a fine-tuned version of [Amadkour/wav2vec2-large-xls-r-300m-tr-softkour](https://huggingface.co/Amadkour/wav2vec2-large-xls-r-300m-tr-softkour) on the common_voice_11_0 dataset.
|
|
|
|
|
|
|
|
|
|
| 19 |
|
| 20 |
## Model description
|
| 21 |
|
|
@@ -43,10 +61,18 @@ The following hyperparameters were used during training:
|
|
| 43 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 44 |
- lr_scheduler_type: linear
|
| 45 |
- lr_scheduler_warmup_steps: 500
|
| 46 |
-
- num_epochs:
|
| 47 |
|
| 48 |
### Training results
|
| 49 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 50 |
|
| 51 |
|
| 52 |
### Framework versions
|
|
|
|
| 1 |
---
|
| 2 |
license: apache-2.0
|
| 3 |
+
base_model: Amadkour/wav2vec2-large-xls-r-300m-tr-softkour
|
| 4 |
tags:
|
| 5 |
- generated_from_trainer
|
|
|
|
| 6 |
datasets:
|
| 7 |
- common_voice_11_0
|
| 8 |
+
metrics:
|
| 9 |
+
- wer
|
| 10 |
model-index:
|
| 11 |
- name: wav2vec2-large-xls-r-300m-tr-softkour
|
| 12 |
+
results:
|
| 13 |
+
- task:
|
| 14 |
+
name: Automatic Speech Recognition
|
| 15 |
+
type: automatic-speech-recognition
|
| 16 |
+
dataset:
|
| 17 |
+
name: common_voice_11_0
|
| 18 |
+
type: common_voice_11_0
|
| 19 |
+
config: ar
|
| 20 |
+
split: test
|
| 21 |
+
args: ar
|
| 22 |
+
metrics:
|
| 23 |
+
- name: Wer
|
| 24 |
+
type: wer
|
| 25 |
+
value: 0.44904159531569354
|
| 26 |
---
|
| 27 |
|
| 28 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
|
| 31 |
# wav2vec2-large-xls-r-300m-tr-softkour
|
| 32 |
|
| 33 |
This model is a fine-tuned version of [Amadkour/wav2vec2-large-xls-r-300m-tr-softkour](https://huggingface.co/Amadkour/wav2vec2-large-xls-r-300m-tr-softkour) on the common_voice_11_0 dataset.
|
| 34 |
+
It achieves the following results on the evaluation set:
|
| 35 |
+
- Loss: 0.4793
|
| 36 |
+
- Wer: 0.4490
|
| 37 |
|
| 38 |
## Model description
|
| 39 |
|
|
|
|
| 61 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 62 |
- lr_scheduler_type: linear
|
| 63 |
- lr_scheduler_warmup_steps: 500
|
| 64 |
+
- num_epochs: 2
|
| 65 |
|
| 66 |
### Training results
|
| 67 |
|
| 68 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
| 69 |
+
|:-------------:|:-----:|:----:|:---------------:|:------:|
|
| 70 |
+
| 0.4662 | 0.33 | 400 | 0.7627 | 0.6241 |
|
| 71 |
+
| 0.3927 | 0.67 | 800 | 0.7286 | 0.6213 |
|
| 72 |
+
| 0.4613 | 1.0 | 1200 | 0.5779 | 0.5185 |
|
| 73 |
+
| 0.4552 | 1.33 | 1600 | 0.5412 | 0.4945 |
|
| 74 |
+
| 0.4145 | 1.66 | 2000 | 0.4922 | 0.4652 |
|
| 75 |
+
| 0.3713 | 2.0 | 2400 | 0.4793 | 0.4490 |
|
| 76 |
|
| 77 |
|
| 78 |
### Framework versions
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1262213380
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f051d012849ef703bc1f449e49169f8d2a0d35fb3522fd11c9389e9055cdd4d9
|
| 3 |
size 1262213380
|