Enable new models in audio-to-text

[eliteprox]

This change adds support for new whisper models distil-whisper/distil-large-v3 and openai/whisper-medium.

The FLOAT16 optimization parameter is also added as an option to optimize speed and memory usage.

{
	"pipeline": "audio-to-text",
	"model_id": "openai/whisper-medium",
	"price_per_unit": 999,
	"warm": true,
	"optimization_flags": {
		"FLOAT16": true
	}
}

Credit to @ad-astra-video for intially exploring these models and optimizations

[rickstaa]

@eliteprox, thanks for the pull request! 🚀 It looks good overall. However, please keep in mind that the default models openai/whisper-large-v3 and distil-whisper/distil-large-v3 use weights in either float16 or bfloat16 formats. The torch_dtype parameter is primarily for the calculations during runtime. You can verify this by checking the model files in these repositories: Hugging Face - distil-large-v3. Notice the presence of files with the .fp32.safetensors extension, indicating the format being used.

If the standard .safetensors (fp16) format meets your needs, you might consider removing the FLOAT16 environment variable and instead switch based on the model extension. This approach was implemented by Yondon in this commit. I will leave that decision to you based on your research 👍🏻. Feel free to merge when you think this pull request is done 🚀.

[eliteprox]

Thanks for the tip, I updated the logic to load recommended float values by model. Tested that they download and load correctly