Automatic Speech Recognition
Transformers
PyTorch
TensorBoard
Hindi
whisper
whisper-event
Generated from Trainer
Eval Results (legacy)
Instructions to use amitkayal/whisper-tiny-hi with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use amitkayal/whisper-tiny-hi with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="amitkayal/whisper-tiny-hi")# Load model directly from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq processor = AutoProcessor.from_pretrained("amitkayal/whisper-tiny-hi") model = AutoModelForSpeechSeq2Seq.from_pretrained("amitkayal/whisper-tiny-hi", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Training in progress, step 1000
Browse files- preprocessor_config.json +1 -1
- pytorch_model.bin +1 -1
preprocessor_config.json
CHANGED
|
@@ -5,7 +5,7 @@
|
|
| 5 |
"hop_length": 160,
|
| 6 |
"mel_filters": [
|
| 7 |
[
|
| 8 |
-
0.0,
|
| 9 |
0.02486259490251541,
|
| 10 |
0.0,
|
| 11 |
0.0,
|
|
|
|
| 5 |
"hop_length": 160,
|
| 6 |
"mel_filters": [
|
| 7 |
[
|
| 8 |
+
-0.0,
|
| 9 |
0.02486259490251541,
|
| 10 |
0.0,
|
| 11 |
0.0,
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 151097331
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c864a5626cd05b7ab4e6427c3a0e1baeac0e007fc59232014ec8bb1aec1b2807
|
| 3 |
size 151097331
|