Automatic Speech Recognition
Transformers
PyTorch
TensorBoard
Belarusian
whisper
whisper-event
Generated from Trainer
Eval Results (legacy)
Instructions to use ales/whisper-tiny-be-test with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use ales/whisper-tiny-be-test with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="ales/whisper-tiny-be-test")# Load model directly from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq processor = AutoProcessor.from_pretrained("ales/whisper-tiny-be-test") model = AutoModelForSpeechSeq2Seq.from_pretrained("ales/whisper-tiny-be-test", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Model save
Browse files
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 151098921
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:71659b8bb8c724d0dee274d075280bc029ec772fe79bbb1ed3842c1b541d7516
|
| 3 |
size 151098921
|
runs/Dec12_19-06-19_13ea4557542f/events.out.tfevents.1670872008.13ea4557542f.5013.0
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 sha256:1d0d9d095e48c0eb71c252899758071f45ab8b038d31c0b20e44976a5a646216
|
| 3 |
+
size 5549
|
train.log
CHANGED
|
@@ -1 +1,3 @@
|
|
| 1 |
{'loss': 2.4473, 'learning_rate': 8.666666666666667e-05, 'epoch': 0.5}
|
|
|
|
|
|
|
|
|
| 1 |
{'loss': 2.4473, 'learning_rate': 8.666666666666667e-05, 'epoch': 0.5}
|
| 2 |
+
{'eval_loss': 1.3674653768539429, 'eval_wer': 95.42124542124543, 'eval_runtime': 44.1027, 'eval_samples_per_second': 1.451, 'eval_steps_per_second': 0.045, 'epoch': 0.5}
|
| 3 |
+
{'loss': 1.256, 'learning_rate': 2e-05, 'epoch': 1.0}
|