Badr Abdullah
commited on
Commit
•
fafd9da
1
Parent(s):
f6bae32
Model save
Browse files
README.md
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
---
|
| 2 |
license: apache-2.0
|
|
|
|
| 3 |
tags:
|
| 4 |
- generated_from_trainer
|
| 5 |
-
base_model: facebook/wav2vec2-xls-r-300m
|
| 6 |
datasets:
|
| 7 |
- common_voice_17_0
|
| 8 |
metrics:
|
|
@@ -11,8 +11,8 @@ model-index:
|
|
| 11 |
- name: xls-r-300m-hbs-phoneme-unfrozen-batch16
|
| 12 |
results:
|
| 13 |
- task:
|
| 14 |
-
type: automatic-speech-recognition
|
| 15 |
name: Automatic Speech Recognition
|
|
|
|
| 16 |
dataset:
|
| 17 |
name: common_voice_17_0
|
| 18 |
type: common_voice_17_0
|
|
@@ -20,22 +20,22 @@ model-index:
|
|
| 20 |
split: test
|
| 21 |
args: hsb
|
| 22 |
metrics:
|
| 23 |
-
-
|
| 24 |
-
|
| 25 |
-
|
| 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 |
-
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/badr-nlp/xlsr-continual-finetuning/runs/
|
| 32 |
# xls-r-300m-hbs-phoneme-unfrozen-batch16
|
| 33 |
|
| 34 |
-
This model is a fine-tuned version of [facebook/wav2vec2-
|
| 35 |
It achieves the following results on the evaluation set:
|
| 36 |
-
- Loss: 0.
|
| 37 |
-
- Wer: 0.
|
| 38 |
-
- Cer: 0.
|
| 39 |
|
| 40 |
## Model description
|
| 41 |
|
|
@@ -70,37 +70,37 @@ The following hyperparameters were used during training:
|
|
| 70 |
|
| 71 |
| Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
|
| 72 |
|:-------------:|:-------:|:----:|:---------------:|:------:|:------:|
|
| 73 |
-
|
|
| 74 |
-
| 3.
|
| 75 |
-
| 3.
|
| 76 |
-
|
|
| 77 |
-
| 0.
|
| 78 |
-
| 0.
|
| 79 |
-
| 0.
|
| 80 |
-
| 0.
|
| 81 |
-
| 0.
|
| 82 |
-
| 0.
|
| 83 |
-
| 0.
|
| 84 |
-
| 0.
|
| 85 |
-
| 0.
|
| 86 |
-
| 0.
|
| 87 |
-
| 0.
|
| 88 |
-
| 0.
|
| 89 |
-
| 0.
|
| 90 |
-
| 0.
|
| 91 |
-
| 0.
|
| 92 |
-
| 0.
|
| 93 |
-
| 0.
|
| 94 |
-
| 0.
|
| 95 |
-
| 0.
|
| 96 |
-
| 0.
|
| 97 |
-
| 0.
|
| 98 |
-
| 0.
|
| 99 |
-
| 0.
|
| 100 |
-
| 0.
|
| 101 |
-
| 0.
|
| 102 |
-
| 0.
|
| 103 |
-
| 0.
|
| 104 |
|
| 105 |
|
| 106 |
### Framework versions
|
|
|
|
| 1 |
---
|
| 2 |
license: apache-2.0
|
| 3 |
+
base_model: facebook/wav2vec2-large-xlsr-53
|
| 4 |
tags:
|
| 5 |
- generated_from_trainer
|
|
|
|
| 6 |
datasets:
|
| 7 |
- common_voice_17_0
|
| 8 |
metrics:
|
|
|
|
| 11 |
- name: xls-r-300m-hbs-phoneme-unfrozen-batch16
|
| 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
|
|
|
|
| 20 |
split: test
|
| 21 |
args: hsb
|
| 22 |
metrics:
|
| 23 |
+
- name: Wer
|
| 24 |
+
type: wer
|
| 25 |
+
value: 0.5337394564198688
|
| 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 |
+
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/badr-nlp/xlsr-continual-finetuning/runs/7duhfamy)
|
| 32 |
# xls-r-300m-hbs-phoneme-unfrozen-batch16
|
| 33 |
|
| 34 |
+
This model is a fine-tuned version of [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) on the common_voice_17_0 dataset.
|
| 35 |
It achieves the following results on the evaluation set:
|
| 36 |
+
- Loss: 0.9205
|
| 37 |
+
- Wer: 0.5337
|
| 38 |
+
- Cer: 0.1244
|
| 39 |
|
| 40 |
## Model description
|
| 41 |
|
|
|
|
| 70 |
|
| 71 |
| Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
|
| 72 |
|:-------------:|:-------:|:----:|:---------------:|:------:|:------:|
|
| 73 |
+
| 4.0877 | 3.2258 | 100 | 3.7799 | 1.0 | 1.0 |
|
| 74 |
+
| 3.2643 | 6.4516 | 200 | 3.2338 | 1.0 | 1.0 |
|
| 75 |
+
| 3.2182 | 9.6774 | 300 | 3.1963 | 1.0 | 1.0 |
|
| 76 |
+
| 0.8009 | 12.9032 | 400 | 0.9289 | 0.8240 | 0.2193 |
|
| 77 |
+
| 0.2664 | 16.1290 | 500 | 0.8523 | 0.7381 | 0.1855 |
|
| 78 |
+
| 0.1359 | 19.3548 | 600 | 0.8465 | 0.6757 | 0.1676 |
|
| 79 |
+
| 0.1022 | 22.5806 | 700 | 0.8537 | 0.6603 | 0.1656 |
|
| 80 |
+
| 0.0641 | 25.8065 | 800 | 0.8821 | 0.6664 | 0.1620 |
|
| 81 |
+
| 0.0565 | 29.0323 | 900 | 0.9185 | 0.6610 | 0.1608 |
|
| 82 |
+
| 0.068 | 32.2581 | 1000 | 0.8839 | 0.6286 | 0.1513 |
|
| 83 |
+
| 0.0556 | 35.4839 | 1100 | 0.8898 | 0.6125 | 0.1479 |
|
| 84 |
+
| 0.0457 | 38.7097 | 1200 | 0.8840 | 0.6204 | 0.1448 |
|
| 85 |
+
| 0.0439 | 41.9355 | 1300 | 0.9207 | 0.6249 | 0.1490 |
|
| 86 |
+
| 0.0296 | 45.1613 | 1400 | 0.9572 | 0.6246 | 0.1510 |
|
| 87 |
+
| 0.0461 | 48.3871 | 1500 | 0.8875 | 0.5918 | 0.1395 |
|
| 88 |
+
| 0.0419 | 51.6129 | 1600 | 0.8967 | 0.5846 | 0.1384 |
|
| 89 |
+
| 0.0333 | 54.8387 | 1700 | 0.9827 | 0.5951 | 0.1420 |
|
| 90 |
+
| 0.0318 | 58.0645 | 1800 | 0.9055 | 0.5733 | 0.1364 |
|
| 91 |
+
| 0.0238 | 61.2903 | 1900 | 0.9497 | 0.5696 | 0.1363 |
|
| 92 |
+
| 0.0257 | 64.5161 | 2000 | 0.9268 | 0.5590 | 0.1330 |
|
| 93 |
+
| 0.0266 | 67.7419 | 2100 | 0.9374 | 0.5703 | 0.1351 |
|
| 94 |
+
| 0.0292 | 70.9677 | 2200 | 0.9304 | 0.5754 | 0.1352 |
|
| 95 |
+
| 0.0288 | 74.1935 | 2300 | 0.9419 | 0.5649 | 0.1334 |
|
| 96 |
+
| 0.0125 | 77.4194 | 2400 | 0.9625 | 0.5581 | 0.1335 |
|
| 97 |
+
| 0.0241 | 80.6452 | 2500 | 0.9449 | 0.5569 | 0.1313 |
|
| 98 |
+
| 0.0217 | 83.8710 | 2600 | 0.9315 | 0.5504 | 0.1292 |
|
| 99 |
+
| 0.0136 | 87.0968 | 2700 | 0.9079 | 0.5373 | 0.1257 |
|
| 100 |
+
| 0.0203 | 90.3226 | 2800 | 0.8935 | 0.5373 | 0.1241 |
|
| 101 |
+
| 0.0166 | 93.5484 | 2900 | 0.9169 | 0.5354 | 0.1239 |
|
| 102 |
+
| 0.0114 | 96.7742 | 3000 | 0.9245 | 0.5323 | 0.1240 |
|
| 103 |
+
| 0.011 | 100.0 | 3100 | 0.9205 | 0.5337 | 0.1244 |
|
| 104 |
|
| 105 |
|
| 106 |
### Framework versions
|