Open-source tools for prompt testing and experimentation, with support for both LLMs (e.g. OpenAI, LLaMA) and vector databases (e.g. Chroma, Weaviate, LanceDB).
Introducing TTA model measurement to prompttools. Similar to LLM and TTI experiments already in place for prompttools, this PR aims to allow for measuring the quality of audio generation models.
Example:
Developer prompts TTA model to generate a described audio
Developer uses prompttools to measure similarity of tta-model-generated audio against real audio seamlessly, and at scale.
Next steps for contributors that are interested:
Complete the experiment framework to work async: /prompttools/prompttools/experiment/experiments/musicgen_experiment.py
Complete the example experiment for quick start: /prompttools/examples/notebooks/audio_experiments/MusicGenExperiment.ipynb
Introducing TTA model measurement to prompttools. Similar to LLM and TTI experiments already in place for prompttools, this PR aims to allow for measuring the quality of audio generation models.
Example:
Next steps for contributors that are interested:
/prompttools/prompttools/experiment/experiments/musicgen_experiment.py
/prompttools/examples/notebooks/audio_experiments/MusicGenExperiment.ipynb