File size: 715 Bytes
a6c0253 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 |
---
language:
- ar
- be
- bg
- bn
- cs
- cy
- da
- de
- el
- en
- es
- et
- fa
- fi
- fr
- gl
- hi
- hu
- it
- ja
- ka
- lt
- lv
- mk
- mr
- nl
- pl
- pt
- ro
- ru
- sk
- sl
- sr
- sv
- sw
- ta
- th
- tr
- uk
- ur
- vi
- zh
library_name: transformers
license: mit
metrics:
- bleu
pipeline_tag: audio-text-to-text
---
Test ultravox model. More coming soon... I hope so.
```python
import transformers
import numpy as np
import librosa
pipe = transformers.pipeline(model='AtAndDev/UVOX-50k-Llama-3.2-1B-Instruct', trust_remote_code=True, device="cuda")
path = "voice_input.mp3"
audio, sr = librosa.load(path, sr=16000)
turns = []
pipe({'audio': audio, 'turns': turns, 'sampling_rate': sr}, max_new_tokens=100)
``` |