End of training
Browse files- README.md +49 -1
- adapter.tha.safetensors +1 -1
- pytorch_model.bin +1 -1
README.md
CHANGED
|
@@ -5,9 +5,24 @@ tags:
|
|
| 5 |
- generated_from_trainer
|
| 6 |
datasets:
|
| 7 |
- common_voice_6_1
|
|
|
|
|
|
|
| 8 |
model-index:
|
| 9 |
- name: wav2vec2-large-mms-1b-thai-colab
|
| 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-mms-1b-thai-colab
|
| 17 |
|
| 18 |
This model is a fine-tuned version of [facebook/mms-1b-all](https://huggingface.co/facebook/mms-1b-all) on the common_voice_6_1 dataset.
|
|
|
|
|
|
|
|
|
|
| 19 |
|
| 20 |
## Model description
|
| 21 |
|
|
@@ -44,6 +62,36 @@ The following hyperparameters were used during training:
|
|
| 44 |
- num_epochs: 4
|
| 45 |
- mixed_precision_training: Native AMP
|
| 46 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 47 |
### Framework versions
|
| 48 |
|
| 49 |
- Transformers 4.35.0.dev0
|
|
|
|
| 5 |
- generated_from_trainer
|
| 6 |
datasets:
|
| 7 |
- common_voice_6_1
|
| 8 |
+
metrics:
|
| 9 |
+
- wer
|
| 10 |
model-index:
|
| 11 |
- name: wav2vec2-large-mms-1b-thai-colab
|
| 12 |
+
results:
|
| 13 |
+
- task:
|
| 14 |
+
name: Automatic Speech Recognition
|
| 15 |
+
type: automatic-speech-recognition
|
| 16 |
+
dataset:
|
| 17 |
+
name: common_voice_6_1
|
| 18 |
+
type: common_voice_6_1
|
| 19 |
+
config: th
|
| 20 |
+
split: test
|
| 21 |
+
args: th
|
| 22 |
+
metrics:
|
| 23 |
+
- name: Wer
|
| 24 |
+
type: wer
|
| 25 |
+
value: 0.7234125438254773
|
| 26 |
---
|
| 27 |
|
| 28 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
|
| 31 |
# wav2vec2-large-mms-1b-thai-colab
|
| 32 |
|
| 33 |
This model is a fine-tuned version of [facebook/mms-1b-all](https://huggingface.co/facebook/mms-1b-all) on the common_voice_6_1 dataset.
|
| 34 |
+
It achieves the following results on the evaluation set:
|
| 35 |
+
- Loss: 0.2452
|
| 36 |
+
- Wer: 0.7234
|
| 37 |
|
| 38 |
## Model description
|
| 39 |
|
|
|
|
| 62 |
- num_epochs: 4
|
| 63 |
- mixed_precision_training: Native AMP
|
| 64 |
|
| 65 |
+
### Training results
|
| 66 |
+
|
| 67 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
| 68 |
+
|:-------------:|:-----:|:----:|:---------------:|:------:|
|
| 69 |
+
| 8.0794 | 0.17 | 100 | 0.3832 | 0.8329 |
|
| 70 |
+
| 0.561 | 0.33 | 200 | 0.3162 | 0.8099 |
|
| 71 |
+
| 0.5132 | 0.5 | 300 | 0.2907 | 0.7842 |
|
| 72 |
+
| 0.5015 | 0.66 | 400 | 0.2954 | 0.7998 |
|
| 73 |
+
| 0.5126 | 0.83 | 500 | 0.2812 | 0.7924 |
|
| 74 |
+
| 0.5182 | 0.99 | 600 | 0.2782 | 0.7631 |
|
| 75 |
+
| 0.4459 | 1.16 | 700 | 0.2735 | 0.7526 |
|
| 76 |
+
| 0.4694 | 1.32 | 800 | 0.2716 | 0.7628 |
|
| 77 |
+
| 0.4576 | 1.49 | 900 | 0.2649 | 0.7538 |
|
| 78 |
+
| 0.4749 | 1.65 | 1000 | 0.2614 | 0.7503 |
|
| 79 |
+
| 0.4282 | 1.82 | 1100 | 0.2687 | 0.7464 |
|
| 80 |
+
| 0.4009 | 1.98 | 1200 | 0.2622 | 0.7480 |
|
| 81 |
+
| 0.3976 | 2.15 | 1300 | 0.2619 | 0.7421 |
|
| 82 |
+
| 0.4306 | 2.31 | 1400 | 0.2620 | 0.7538 |
|
| 83 |
+
| 0.4413 | 2.48 | 1500 | 0.2551 | 0.7515 |
|
| 84 |
+
| 0.3888 | 2.64 | 1600 | 0.2545 | 0.7339 |
|
| 85 |
+
| 0.4213 | 2.81 | 1700 | 0.2541 | 0.7316 |
|
| 86 |
+
| 0.3945 | 2.98 | 1800 | 0.2507 | 0.7246 |
|
| 87 |
+
| 0.3765 | 3.14 | 1900 | 0.2495 | 0.7234 |
|
| 88 |
+
| 0.3859 | 3.31 | 2000 | 0.2498 | 0.7269 |
|
| 89 |
+
| 0.3931 | 3.47 | 2100 | 0.2469 | 0.7250 |
|
| 90 |
+
| 0.3737 | 3.64 | 2200 | 0.2470 | 0.7242 |
|
| 91 |
+
| 0.3716 | 3.8 | 2300 | 0.2454 | 0.7219 |
|
| 92 |
+
| 0.3582 | 3.97 | 2400 | 0.2452 | 0.7234 |
|
| 93 |
+
|
| 94 |
+
|
| 95 |
### Framework versions
|
| 96 |
|
| 97 |
- Transformers 4.35.0.dev0
|
adapter.tha.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 9008632
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:715d0417de64dc187585235a14f390175b159e5ea0655c1b8d3038c190a991e8
|
| 3 |
size 9008632
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 3859344653
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f9cac86f5f9fb72bac8879f7511056ccbd992592174621e0f78ec8595ff6cd7e
|
| 3 |
size 3859344653
|