Build local voice agents with open-source models
huggingface/speech-to-speech is drawing steady momentum at +8.1 stars/day (67th percentile in the tracked cohort), for a momentum score of 67.7/100. A recent release is helping fuel the run.
Reconstructed from 253 snapshots — the time-series GitHub’s API doesn’t expose.
Release count rose to 6.
~18 forks/day, 4.8× the trailing baseline.
~10 forks/day, 4.5× the trailing baseline.
Live score, refreshed every 6 hours. Links back to this page.
[](https://repoclimb.com/repo/huggingface/speech-to-speech)Moderate breakout odds over the next 14 days, led by star acceleration (62th pctl) and push recency (98th pctl). Confidence is high given the available history.
Transparent heuristic · logged for model training
Percentile rank within the tracked cohort. The score self-calibrates — it answers “accelerating vs. everything else,” not raw size.
~13 forks/day, 4.4× the trailing baseline.
~21 forks/day, 3.2× the trailing baseline.
~19 forks/day, 7.6× the trailing baseline.
~17 forks/day, 28.1× the trailing baseline.
Release count rose to 5.
~64 forks/day, 17.5× the trailing baseline.
~10 forks/day, 3.4× the trailing baseline.
~32 forks/day, 7.7× the trailing baseline.
~13 forks/day, 4.0× the trailing baseline.