Model save
Browse files
README.md
CHANGED
|
@@ -3,9 +3,6 @@ library_name: transformers
|
|
| 3 |
license: cc-by-nc-4.0
|
| 4 |
base_model: facebook/mms-1b-all
|
| 5 |
tags:
|
| 6 |
-
- automatic-speech-recognition
|
| 7 |
-
- bigcgen
|
| 8 |
-
- mms
|
| 9 |
- generated_from_trainer
|
| 10 |
metrics:
|
| 11 |
- wer
|
|
@@ -19,10 +16,10 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 19 |
|
| 20 |
# mms-1b-bigcgen-combined-30hrs-model
|
| 21 |
|
| 22 |
-
This model is a fine-tuned version of [facebook/mms-1b-all](https://huggingface.co/facebook/mms-1b-all) on
|
| 23 |
It achieves the following results on the evaluation set:
|
| 24 |
- Loss: inf
|
| 25 |
-
- Wer: 0.
|
| 26 |
|
| 27 |
## Model description
|
| 28 |
|
|
@@ -50,17 +47,38 @@ The following hyperparameters were used during training:
|
|
| 50 |
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 51 |
- lr_scheduler_type: linear
|
| 52 |
- lr_scheduler_warmup_steps: 100
|
| 53 |
-
-
|
| 54 |
- mixed_precision_training: Native AMP
|
| 55 |
|
| 56 |
### Training results
|
| 57 |
|
| 58 |
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
| 59 |
|:-------------:|:------:|:----:|:---------------:|:------:|
|
| 60 |
-
| 14.
|
| 61 |
-
| 6.
|
| 62 |
-
|
|
| 63 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 64 |
|
| 65 |
|
| 66 |
### Framework versions
|
|
|
|
| 3 |
license: cc-by-nc-4.0
|
| 4 |
base_model: facebook/mms-1b-all
|
| 5 |
tags:
|
|
|
|
|
|
|
|
|
|
| 6 |
- generated_from_trainer
|
| 7 |
metrics:
|
| 8 |
- wer
|
|
|
|
| 16 |
|
| 17 |
# mms-1b-bigcgen-combined-30hrs-model
|
| 18 |
|
| 19 |
+
This model is a fine-tuned version of [facebook/mms-1b-all](https://huggingface.co/facebook/mms-1b-all) on an unknown dataset.
|
| 20 |
It achieves the following results on the evaluation set:
|
| 21 |
- Loss: inf
|
| 22 |
+
- Wer: 0.5079
|
| 23 |
|
| 24 |
## Model description
|
| 25 |
|
|
|
|
| 47 |
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 48 |
- lr_scheduler_type: linear
|
| 49 |
- lr_scheduler_warmup_steps: 100
|
| 50 |
+
- training_steps: 2500
|
| 51 |
- mixed_precision_training: Native AMP
|
| 52 |
|
| 53 |
### Training results
|
| 54 |
|
| 55 |
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
| 56 |
|:-------------:|:------:|:----:|:---------------:|:------:|
|
| 57 |
+
| 14.5866 | 0.0509 | 100 | inf | 1.0167 |
|
| 58 |
+
| 6.2466 | 0.1018 | 200 | inf | 1.0019 |
|
| 59 |
+
| 5.4142 | 0.1526 | 300 | inf | 0.9912 |
|
| 60 |
+
| 2.1374 | 0.2035 | 400 | inf | 0.5952 |
|
| 61 |
+
| 1.741 | 0.2544 | 500 | inf | 0.5641 |
|
| 62 |
+
| 1.6543 | 0.3053 | 600 | inf | 0.5607 |
|
| 63 |
+
| 1.6579 | 0.3561 | 700 | inf | 0.5585 |
|
| 64 |
+
| 1.676 | 0.4070 | 800 | inf | 0.5475 |
|
| 65 |
+
| 1.5245 | 0.4579 | 900 | inf | 0.5410 |
|
| 66 |
+
| 1.6324 | 0.5088 | 1000 | inf | 0.5278 |
|
| 67 |
+
| 1.6878 | 0.5597 | 1100 | inf | 0.5244 |
|
| 68 |
+
| 1.4994 | 0.6105 | 1200 | inf | 0.5259 |
|
| 69 |
+
| 1.544 | 0.6614 | 1300 | inf | 0.5211 |
|
| 70 |
+
| 1.5796 | 0.7123 | 1400 | inf | 0.5244 |
|
| 71 |
+
| 1.3625 | 0.7632 | 1500 | inf | 0.5235 |
|
| 72 |
+
| 1.4826 | 0.8140 | 1600 | inf | 0.5165 |
|
| 73 |
+
| 1.4439 | 0.8649 | 1700 | inf | 0.5227 |
|
| 74 |
+
| 1.4778 | 0.9158 | 1800 | inf | 0.5148 |
|
| 75 |
+
| 1.389 | 0.9667 | 1900 | inf | 0.5130 |
|
| 76 |
+
| 1.3863 | 1.0173 | 2000 | inf | 0.5177 |
|
| 77 |
+
| 1.516 | 1.0682 | 2100 | inf | 0.5082 |
|
| 78 |
+
| 1.474 | 1.1191 | 2200 | inf | 0.5106 |
|
| 79 |
+
| 1.465 | 1.1699 | 2300 | inf | 0.5077 |
|
| 80 |
+
| 1.484 | 1.2208 | 2400 | inf | 0.5090 |
|
| 81 |
+
| 1.3942 | 1.2717 | 2500 | inf | 0.5079 |
|
| 82 |
|
| 83 |
|
| 84 |
### Framework versions
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 3858885800
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b9ea58367f382b0863e69d30c6ac13d299d5f15c54ad82ab757c476fbdd0491e
|
| 3 |
size 3858885800
|
runs/Dec29_05-05-20_srvrocgpu011.uct.ac.za/events.out.tfevents.1735441723.srvrocgpu011.uct.ac.za
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:a13ab46010a3aadb906f084381e0d195b3288e985650e159cfb0ae176beeacae
|
| 3 |
+
size 20148
|