-
## Feature Name
Stability AI
## Feature Description
## Overview of Stability AI
**Stability AI** is a leading company in the field of generative AI, recognized for its open-source models a…
-
Dear,
I have setup a whep player to webrtc server on ESP, so I have a problem with connect media stream after get offer successs.
Could you give me advise? Thanks!
More log for details:
```
Res…
-
I am using whisperx for inference (which is built upon faster-whisper).
I have finetuned large-v3 model on 1k hours of domain-specific data. When I run standard inference the results are ok. Finetu…
-
**Is your feature request related to a problem? Please describe.**
The current chunking method can split text into parts that are too long for the model, leading to reduced quality, skipped words, or…
-
## Goal
Experiment on WhisperVQ model for better result on multilingual. Hypothesis the current codebook is only 512 which is a small space to compress the multilingual capability.
## Learning Goa…
-
Hi.
It would be great if you could add an example of extracting data from incoming audio messages. This may be useful for further translation of them into text and sending them to GPT similar service…
-
### System Info
- `transformers` version: 4.46.2
- Platform: Linux-5.4.0-1134-aws-x86_64-with-glibc2.31
- Python version: 3.10.2
- Huggingface_hub version: 0.26.2
- Safetensors version: 0.4.5
- …
-
**Describe the bug**
If I switch to nvidia envycontrol -q says it's set to nvidia but everything seems like it's in hybrid mode.
If I launch nvidia-settings it still shows the intel GPU running a …
-
这是我的代码
from transformers import AutoModelForCausalLM, AutoTokenizer
from transformers.generation import GenerationConfig
import torch
import re
import os
import glob
import time
torch.man…
-
Is there a way to get this to do function calling (tool use)?