Instructions to use nyrahealth/CrisperWhisper with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use nyrahealth/CrisperWhisper with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="nyrahealth/CrisperWhisper")# Load model directly from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq processor = AutoProcessor.from_pretrained("nyrahealth/CrisperWhisper") model = AutoModelForSpeechSeq2Seq.from_pretrained("nyrahealth/CrisperWhisper") - Notebooks
- Google Colab
- Kaggle
How to output sentence-level text with timestamps?
❤️ 1
1
#21 opened 12 months ago
by
aimagee
RuntimeError: The expanded size of the tensor (54) must match the existing size (57) at non-singleton dimension 1. Target sizes: [1, 54]. Tensor sizes: [57]
#20 opened about 1 year ago
by
vian123
Adds GGML model (8-bit)
#19 opened about 1 year ago
by
Naataan
Adds GGML model file (16-bit)
#18 opened about 1 year ago
by
Naataan
Is anyone experiencing the connection issue?
#17 opened about 1 year ago
by
cassielee
Only works with English and German with the FasterWhisper version
#16 opened about 1 year ago
by
David526sky
The new Nvidia 50 series graphics cards, such as the 5070Ti, are not supported. Please optimize and add support.
#15 opened about 1 year ago
by
dyqiang
Diarization
1
#14 opened over 1 year ago
by
swtb
Don't get pauses back
3
#13 opened over 1 year ago
by
daniel8845
Support for Italian language?
2
#12 opened over 1 year ago
by
ManuSri
Support `whisper.cpp` in the future?
👍 3
1
#11 opened over 1 year ago
by
BenjaminChu
Smaller versions?
1
#7 opened over 1 year ago
by
hammeiam
num_beams less than 5 not working?
#6 opened over 1 year ago
by
kdcyberdude
Onnx version?
1
#4 opened over 1 year ago
by
hammeiam
IndexError: list index out of range
1
#3 opened over 1 year ago
by
MatBar99
How do we use with cli?
#1 opened over 1 year ago
by
MonsterMMORPG