skit-ai/SpeechLLM

This repository contains the training, inference, evaluation code for SpeechLLM models and details about the model releases on huggingface.

40
/ 100
Emerging

This helps professionals who analyze spoken interactions to extract key details. By inputting an audio file of someone speaking, it can tell you if there's speech, provide a transcript, and identify the speaker's gender, age group, accent, and emotional state. This is useful for anyone reviewing calls, interviews, or spoken content.

130 stars. No commits in the last 6 months.

Use this if you need to quickly get a transcript and detailed demographic/emotional metadata from short audio clips of speech.

Not ideal if you require absolute accuracy for sensitive applications, as the model may produce errors and exhibits biases.

call-center-analytics customer-feedback interview-analysis voice-of-customer audio-content-analysis
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 14 / 25

How are scores calculated?

Stars

130

Forks

15

Language

Python

License

Apache-2.0

Last pushed

Jun 25, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/skit-ai/SpeechLLM"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.