Automatic Speech Recognition
Transformers
Safetensors
English
voxtral_realtime
audio
multimodal
emotion-recognition
customer-support
emergency-services
sft
trl
hf_jobs
Instructions to use trishtan/voxtral-sentinel-4b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use trishtan/voxtral-sentinel-4b with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="trishtan/voxtral-sentinel-4b")# Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("trishtan/voxtral-sentinel-4b") model = AutoModelForMultimodalLM.from_pretrained("trishtan/voxtral-sentinel-4b", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Commit ·
5b6ffde
1
Parent(s): 6bcbfd4
Update README.md
Browse files
README.md
CHANGED
|
@@ -17,14 +17,7 @@ It has been trained using [TRL](https://github.com/huggingface/trl).
|
|
| 17 |
|
| 18 |
## Quick start
|
| 19 |
|
| 20 |
-
|
| 21 |
-
from transformers import pipeline
|
| 22 |
-
|
| 23 |
-
question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
|
| 24 |
-
generator = pipeline("text-generation", model="trishtan/voxtral-sentinel-4b", device="cuda")
|
| 25 |
-
output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
|
| 26 |
-
print(output["generated_text"])
|
| 27 |
-
```
|
| 28 |
|
| 29 |
## Training procedure
|
| 30 |
|
|
|
|
| 17 |
|
| 18 |
## Quick start
|
| 19 |
|
| 20 |
+
We deleted the quick start code because that's a ASR model, not a text generation model.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 21 |
|
| 22 |
## Training procedure
|
| 23 |
|