Initial upload of multi-instrument MIDI transcription models

README.md

@@ -1,21 +1,17 @@
 ---
 license: mit
+pipeline_tag: audio-to-midi
 tags:
 - audio
 - midi
 - model_hub_mixin
+- multi-instrument
 - music
 - pytorch_model_hub_mixin
-- saxophone
-- bass
-- piano
-- guitar
 - transcription
 ---
 
+This model has been pushed to the Hub using the [PytorchModelHubMixin](https://huggingface.co/docs/huggingface_hub/package_reference/mixins#huggingface_hub.PyTorchModelHubMixin) integration:
 - Code: https://github.com/xavriley/hf_midi_transcription/
-- Paper (sax): https://arxiv.org/abs/2405.16687
-- Paper (bass): https://arxiv.org/abs/2311.02023
-- Paper (piano): https://arxiv.org/abs/2010.01815
-- Paper (guitar 1): https://arxiv.org/pdf/2402.15258
-- Paper (guitar 2): https://arxiv.org/abs/2408.08653
+- Paper: [More Information Needed]
+- Docs: [More Information Needed]

config.json

@@ -0,0 +1,6 @@
+{
+  "batch_size": 8,
+  "checkpoint_path": "filosax_25k.pth",
+  "device": "cpu",
+  "instrument": "saxophone"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:95834d9dea68263da602eebe8c5c2c065110c8647b27679308b050f1e14ad91a
+size 76