Most-recent-first list of my Claude fine-tunings
Andrew DeLisa
ayan4m1
AI & ML interests
Distilled fine-tuning
Recent Activity
reacted to ksrupaakula's post with 👍 12 minutes ago
Evaluating ASR beyond short clips: our Numo Indic Speech releases provide longer-form transcribed audio across four languages:
Hindi: 46.6s average duration
Telugu: 33.3s
Tamil: 32.7s
Bengali: 46.5s
For comparison, Common Voice 26.0 averages roughly 4–6 seconds across these languages.
These longer recordings support research into segmentation, context retention, streaming, and endpointing behavior.
The four datasets are available under controlled access. Check them out: https://huggingface.co/datasets/psdn-ai/numo-indic-speech upvoted a collection 7 days ago
flux-3-image-klein (prompt-upsampler) upvoted a changelog 9 days ago
Passkeys for sign-in and MFAOrganizations
models 22
ayan4m1/Clemma-12B-GGUF
Image-Text-to-Text • 12B • Updated • 771
ayan4m1/Clemma-12B
Image-Text-to-Text • 12B • Updated • 61
ayan4m1/kev-9b-merged
Image-Text-to-Text • 10B • Updated • 120
ayan4m1/kev-4b-merged
Image-Text-to-Text • 3B • Updated • 101
ayan4m1/kev-0.8b-merged
Image-Text-to-Text • 0.6B • Updated • 183
ayan4m1/kev-9b-merged-gguf
Image-Text-to-Text • 9B • Updated • 876
ayan4m1/kev-4b-merged-gguf
4B • Updated • 750
ayan4m1/kev-0.8b-merged-gguf
Image-Text-to-Text • 0.8B • Updated • 788
ayan4m1/Qwen2.5-Coder-14B-E2E-Tests
Text Generation • 15B • Updated • 24 • 1
ayan4m1/Qwen3.5-4B-E2E-Tests-GGUF
Image-Text-to-Text • 4B • Updated • 292