matbee

I need DEFLATE support with a level 0 compression, having trouble with implementation though.

Audio Performance

1

I notice there is a lot of clicking when the audio initially outputs, which causes the first 1-2 words to become incoherent. Is there a way to increase audio performance?

Enable x264 for transcoding audio of container with x264 video tracks.

1

I would really like to see x264 enabled so I can "copy" the video tracks from the container, while only transcoding the audio tracks! :)

Default to system CPU thread count

2

Instead of defaulting to 8, default to system CPU.

Yes it's a little bit muddled up with my previous PR, can clean up if necessary, would prefer not to :)

Using latest `main` ``` (textgen) acidhax@PC:~/text-generation-webui$ python server.py --listen --auto-devices --model llama-13b-hf --gptq-bits 4 Loading llama-13b-hf... Traceback (most recent call last): File "/home/acidhax/text-generation-webui/server.py", line 242, in shared.model, shared.tokenizer = load_model(shared.model_name)...

I'm looking for a solution that can ultimately listen to an audio-out device (audio in is possible but I dislike that route for users), and run speaker diarization so split...

Support onnx export of microsoft/speecht5_hifigan and microsoft/speecht5_vc

1

### Feature request # microsoft/speecht5_vc ``` ValueError: Asked to export a speecht5 model for the task audio-to-audio (auto-detected), but the Optimum ONNX exporter only supports the tasks text-to-audio for speecht5....

Added support for OpenAI's Multimodal messages format, Enabled CORS headers

18

Allows for inference via openai's api sdk. ``` const response = await openai.chat.completions.create({ model: MultiModalLanguage.model, messages: [ { role: 'system', content: MultiModalLanguage.system }, { role: 'user', content: [ { type:...