Instructions to use ibm-granite/granite-speech-3.3-8b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use ibm-granite/granite-speech-3.3-8b with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="ibm-granite/granite-speech-3.3-8b")# Load model directly from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq processor = AutoProcessor.from_pretrained("ibm-granite/granite-speech-3.3-8b") model = AutoModelForSpeechSeq2Seq.from_pretrained("ibm-granite/granite-speech-3.3-8b") - Notebooks
- Google Colab
- Kaggle
GGUF + pure-C++ runtime in CrispASR — Granite 3.3-8B
#23 opened about 1 month ago
by
cstr
granite-speech repeat word on long audio with vllm
5
#21 opened 3 months ago
by
jonathmartel
Flash Attention v2 doesnt work
1
#20 opened 6 months ago
by
abcdefghijklmnop52
fine tune for LLM tasks
1
#19 opened 7 months ago
by
itaipee
Incomplete Transcripts (with Transformers package)
1
#17 opened 9 months ago
by
KevinN15
Dear author, I would like to know what is the minimum version of VLLM required to run this model?
1
#13 opened 11 months ago
by
Tree1995
Scripts fpr finetuning this model on custom data
🤝 1
15
#9 opened 12 months ago
by
Mrigank
Problems with word insertions (hallucinations) when used with vLLM (online)
5
#4 opened about 1 year ago
by
entn-at
Add Guidance for Repetition Penalty
#2 opened about 1 year ago
by
abrooks9944
Local Installation Video and Testing - Step by Step
❤️ 6
2
#1 opened about 1 year ago
by
fahdmirzac