restore the training checkpoint

note where the training checkpoint lives

remove the training checkpoint; a verified copy is at /media/hdd16/phoonnx-training-checkpoints/phoonnx_gl-ES_miro_unicode/epoch=78-step=93852.ckpt

replace the sample: the previous one was synthesized with the default voice

add a sample of this voice

docs: correct lineage wording (fine-tuned from closest-language base)

docs: remove incorrect voice-conversion base-model claim

docs: full model card (ownership, usage, datasets)

Create README.md

Upload 3 files

initial commit