Commit
•
fcfb3f6
1
Parent(s):
51d14d5
stillerman/stammer-libristutter-small
Browse files
README.md
CHANGED
|
@@ -3,8 +3,6 @@ license: apache-2.0
|
|
| 3 |
base_model: openai/whisper-small
|
| 4 |
tags:
|
| 5 |
- generated_from_trainer
|
| 6 |
-
metrics:
|
| 7 |
-
- wer
|
| 8 |
model-index:
|
| 9 |
- name: stammer-libristutter-small
|
| 10 |
results: []
|
|
@@ -17,8 +15,13 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 17 |
|
| 18 |
This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the None dataset.
|
| 19 |
It achieves the following results on the evaluation set:
|
| 20 |
-
-
|
| 21 |
-
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 22 |
|
| 23 |
## Model description
|
| 24 |
|
|
@@ -43,20 +46,10 @@ The following hyperparameters were used during training:
|
|
| 43 |
- seed: 42
|
| 44 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 45 |
- lr_scheduler_type: linear
|
| 46 |
-
- lr_scheduler_warmup_steps:
|
| 47 |
-
- training_steps:
|
| 48 |
- mixed_precision_training: Native AMP
|
| 49 |
|
| 50 |
-
### Training results
|
| 51 |
-
|
| 52 |
-
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
| 53 |
-
|:-------------:|:-----:|:----:|:---------------:|:-------:|
|
| 54 |
-
| 1.1664 | 0.25 | 8 | 0.9333 | 36.5739 |
|
| 55 |
-
| 0.7815 | 0.5 | 16 | 0.5958 | 20.2668 |
|
| 56 |
-
| 0.5303 | 0.75 | 24 | 0.4729 | 18.3225 |
|
| 57 |
-
| 0.4116 | 1.0 | 32 | 0.4182 | 18.2373 |
|
| 58 |
-
|
| 59 |
-
|
| 60 |
### Framework versions
|
| 61 |
|
| 62 |
- Transformers 4.43.2
|
|
|
|
| 3 |
base_model: openai/whisper-small
|
| 4 |
tags:
|
| 5 |
- generated_from_trainer
|
|
|
|
|
|
|
| 6 |
model-index:
|
| 7 |
- name: stammer-libristutter-small
|
| 8 |
results: []
|
|
|
|
| 15 |
|
| 16 |
This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the None dataset.
|
| 17 |
It achieves the following results on the evaluation set:
|
| 18 |
+
- eval_loss: 0.2804
|
| 19 |
+
- eval_wer: 18.7648
|
| 20 |
+
- eval_runtime: 69.9551
|
| 21 |
+
- eval_samples_per_second: 2.859
|
| 22 |
+
- eval_steps_per_second: 0.357
|
| 23 |
+
- epoch: 2.56
|
| 24 |
+
- step: 128
|
| 25 |
|
| 26 |
## Model description
|
| 27 |
|
|
|
|
| 46 |
- seed: 42
|
| 47 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 48 |
- lr_scheduler_type: linear
|
| 49 |
+
- lr_scheduler_warmup_steps: 32
|
| 50 |
+
- training_steps: 256
|
| 51 |
- mixed_precision_training: Native AMP
|
| 52 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 53 |
### Framework versions
|
| 54 |
|
| 55 |
- Transformers 4.43.2
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 966995080
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ca6d0794f12fa54ed035a5ef255e34b71c9039009f4868727febecec3586d60a
|
| 3 |
size 966995080
|
runs/Jul24_20-11-18_42f1b3e6cea2/events.out.tfevents.1721851885.42f1b3e6cea2.8883.0
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:c88e684a1381c5ebc2d636dbc994a0fc860a128d5879b488adf88dcbd708d91c
|
| 3 |
+
size 11483
|