Upload folder using huggingface_hub

README.md

@@ -17,12 +17,12 @@ models described in our paper (under review). Each checkpoint greedily decodes a
 Humdrum `**kern` lead sheet (melody `**kern`, chords `**cdata`, lyrics `**text`)
 from pre-computed [MuQ](https://github.com/tencent-ailab/MuQ) features.
 
-| file | lyrics tokeniser |
+| file | lyrics tokeniser (`--lyrics_tokeniser`) |
 |---|---|
-| `final_no_lyrics_augmented.ckpt` | none |
-| `final_syllable_augmented.ckpt` | syllable |
-| `final_char_augmented.ckpt` | character |
-| `final_bpe_augmented.ckpt` | BPE (GPT-2) |
+| `cummins_retrained.ckpt` | `none` |
+| `word_tok.ckpt` | `word` |
+| `char_tok.ckpt` | `character` |
+| `bpe_tok.ckpt` | `bpe` (GPT-2) |
 
 Inference and evaluation code: [GitHub repository](https://github.com/Multimodal-Music-Research-Lab/Audio-to-Lead-Sheet-Transcription).
 

bpe_tok.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:612226e904f04d77723eb206da7cf091724e9795a7c8d18ac0ec985bf2f24828
+size 471510834

char_tok.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:19a83af9fb9aaeac67efb1a6245cfbe8a87f897bb6aeaf341acb52fe6f8f1169
+size 160908978

cummins_retrained.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:12219c5a179685c7c73c4ca82b3ce738a2835f0c7ed28f9f8f68dd23a20e6145
+size 159722738

word_tok.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c1489f4b7823a80ea33c829e4666a968c9a17e8ea94088aa7b1432c1d93e9677
+size 379303282