End of training
Browse files- README.md +21 -1
- adapter.twi.safetensors +2 -2
- pytorch_model.bin +1 -1
README.md
CHANGED
|
@@ -3,6 +3,8 @@ license: cc-by-nc-4.0
|
|
| 3 |
base_model: facebook/mms-1b-all
|
| 4 |
tags:
|
| 5 |
- generated_from_trainer
|
|
|
|
|
|
|
| 6 |
model-index:
|
| 7 |
- name: wav2vec2-large-mms-1b-twi-colab
|
| 8 |
results: []
|
|
@@ -14,6 +16,9 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 14 |
# wav2vec2-large-mms-1b-twi-colab
|
| 15 |
|
| 16 |
This model is a fine-tuned version of [facebook/mms-1b-all](https://huggingface.co/facebook/mms-1b-all) on the None dataset.
|
|
|
|
|
|
|
|
|
|
| 17 |
|
| 18 |
## Model description
|
| 19 |
|
|
@@ -39,10 +44,25 @@ The following hyperparameters were used during training:
|
|
| 39 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 40 |
- lr_scheduler_type: linear
|
| 41 |
- lr_scheduler_warmup_steps: 100
|
| 42 |
-
- num_epochs:
|
| 43 |
|
| 44 |
### Training results
|
| 45 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 46 |
|
| 47 |
|
| 48 |
### Framework versions
|
|
|
|
| 3 |
base_model: facebook/mms-1b-all
|
| 4 |
tags:
|
| 5 |
- generated_from_trainer
|
| 6 |
+
metrics:
|
| 7 |
+
- wer
|
| 8 |
model-index:
|
| 9 |
- name: wav2vec2-large-mms-1b-twi-colab
|
| 10 |
results: []
|
|
|
|
| 16 |
# wav2vec2-large-mms-1b-twi-colab
|
| 17 |
|
| 18 |
This model is a fine-tuned version of [facebook/mms-1b-all](https://huggingface.co/facebook/mms-1b-all) on the None dataset.
|
| 19 |
+
It achieves the following results on the evaluation set:
|
| 20 |
+
- Loss: 0.5085
|
| 21 |
+
- Wer: 0.4664
|
| 22 |
|
| 23 |
## Model description
|
| 24 |
|
|
|
|
| 44 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 45 |
- lr_scheduler_type: linear
|
| 46 |
- lr_scheduler_warmup_steps: 100
|
| 47 |
+
- num_epochs: 100
|
| 48 |
|
| 49 |
### Training results
|
| 50 |
|
| 51 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
| 52 |
+
|:-------------:|:-----:|:----:|:---------------:|:------:|
|
| 53 |
+
| 7.6457 | 7.69 | 100 | 1.0843 | 0.8419 |
|
| 54 |
+
| 0.7832 | 15.38 | 200 | 0.4796 | 0.5296 |
|
| 55 |
+
| 0.5053 | 23.08 | 300 | 0.4547 | 0.4783 |
|
| 56 |
+
| 0.4083 | 30.77 | 400 | 0.4349 | 0.4545 |
|
| 57 |
+
| 0.3281 | 38.46 | 500 | 0.4467 | 0.4506 |
|
| 58 |
+
| 0.276 | 46.15 | 600 | 0.4482 | 0.4427 |
|
| 59 |
+
| 0.2269 | 53.85 | 700 | 0.4847 | 0.4664 |
|
| 60 |
+
| 0.2081 | 61.54 | 800 | 0.4704 | 0.4150 |
|
| 61 |
+
| 0.1974 | 69.23 | 900 | 0.5047 | 0.4506 |
|
| 62 |
+
| 0.1695 | 76.92 | 1000 | 0.5142 | 0.4625 |
|
| 63 |
+
| 0.1642 | 84.62 | 1100 | 0.5028 | 0.4625 |
|
| 64 |
+
| 0.159 | 92.31 | 1200 | 0.5085 | 0.4664 |
|
| 65 |
+
| 0.1581 | 100.0 | 1300 | 0.5085 | 0.4664 |
|
| 66 |
|
| 67 |
|
| 68 |
### Framework versions
|
adapter.twi.safetensors
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 sha256:154e8c1c0ba9e8cb1826b2f490b9d2d765e29c5ff97dd32c1fcd36864e8b9364
|
| 3 |
+
size 8854904
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 3859190925
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6e5946fd8e2302b99c3950fffa20a6d62b5175d9ff3b393c7c1bc8bc3a84faa0
|
| 3 |
size 3859190925
|