Automatic Speech Recognition
Transformers
PyTorch
TensorBoard
Safetensors
Northern Sami
whisper
whisper-event
Generated from Trainer
Eval Results (legacy)
Instructions to use NbAiLab/whisper-large-sme with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use NbAiLab/whisper-large-sme with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="NbAiLab/whisper-large-sme")# Load model directly from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq processor = AutoProcessor.from_pretrained("NbAiLab/whisper-large-sme") model = AutoModelForSpeechSeq2Seq.from_pretrained("NbAiLab/whisper-large-sme", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Add OpenAI Whisper format
Browse files- cli.py +5 -0
- convert_to_openai.py +7 -0
- whisper-large-sme.pt +3 -0
cli.py
ADDED
|
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
import whisper
|
| 2 |
+
|
| 3 |
+
whisper._MODELS["NbAiLab/whisper-large-sme"] = ""
|
| 4 |
+
from whiper.transcribe import cli
|
| 5 |
+
from
|
convert_to_openai.py
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
#!/usr/bin/env python
|
| 2 |
+
# !pip install git+https://github.com/bayartsogt-ya/whisper-multiple-hf-datasets.git
|
| 3 |
+
|
| 4 |
+
from multiple_datasets.hub_default_utils import convert_hf_whisper
|
| 5 |
+
model_name_or_path = './'
|
| 6 |
+
whisper_checkpoint_path = './whisper-large-sme.pt'
|
| 7 |
+
convert_hf_whisper(model_name_or_path, whisper_checkpoint_path)
|
whisper-large-sme.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bed43f50f06fd0db81c1009d7d9cbc2c595c5f7f6a6278e137410fea92d15f28
|
| 3 |
+
size 6173677996
|