update_files (#2)

- files added (11b15ddffff9cd12297afb0da579eadd43c99321)


Co-authored-by: Susnato Dhar <susnato@users.noreply.huggingface.co>

README.md

@@ -1,12 +1,67 @@
 ---
-license: mit
-metrics:
-- accuracy
-tags:
-- piano cover generation
-datasets:
-- PSP
-references:
-- https://arxiv.org/abs/2211.00895
+# For reference on model card metadata, see the spec: https://github.com/huggingface/hub-docs/blob/main/modelcard.md?plain=1
+# Doc / guide: https://huggingface.co/docs/hub/model-cards
+{}
 ---
-.
+
+# POP2PIANO
+
+Pop2Piano, a Transformer network that generates piano covers given waveforms of pop
+music.
+# Model Details
+
+Pop2Piano was proposed in the paper [Pop2Piano : Pop Audio-based Piano Cover Generation](https://arxiv.org/abs/2211.00895) by Jongho Choi and Kyogu Lee.
+
+Inspired by [T5](https://arxiv.org/abs/1910.10683), Pop2Piano
+is the first model to generate a piano cover directly from pop audio without using melody and
+chord extraction modules.
+
+## Model Sources
+
+- [**Original Repository**](https://github.com/sweetcocoa/pop2piano)
+- [**Paper**](https://arxiv.org/abs/2211.00895)
+- [**Demo**]# TODO (after the ongoing PR is merged)
+
+# Usage
+
+First, install the required packages:
+
+```
+pip install --upgrade transformers
+```
+
+## Pop music to Piano
+
+ TODO (after the ongoing PR is merged)
+
+## Example 
+
+### Pop Music
+
+<audio controls>
+    <source src="https://datasets-server.huggingface.co/assets/sweetcocoa/pop2piano_ci/--/sweetcocoa--pop2piano_ci/test/0/audio/audio.mp3" type="audio/mpeg">
+Your browser does not support the audio element.
+</audio>
+
+### Generated MIDI
+
+TODO (after the MIDI version is uploaded to the same repo above)
+
+## Tips
+
+ TODO
+
+
+# Citation
+
+**BibTeX:**
+```
+@misc{choi2023pop2piano,
+      title={Pop2Piano : Pop Audio-based Piano Cover Generation}, 
+      author={Jongho Choi and Kyogu Lee},
+      year={2023},
+      eprint={2211.00895},
+      archivePrefix={arXiv},
+      primaryClass={cs.SD}
+}
+```

config.json

@@ -32,5 +32,6 @@
     "n_fft":4096,
     "hop_length":1024,
     "f_min":10.0,
-    "n_mels":512
+    "n_mels":512,
+    "composer_vocab_size":21
 }

generation_config.json

@@ -0,0 +1,30 @@
+{
+  "decoder_start_token_id": 0,
+  "eos_token_id": 1,
+  "pad_token_id": 0,
+  "return_dict_in_generate": false,
+  "max_length": 256,
+  "composer_to_feature_token":{
+    "composer1": 2052,
+    "composer2": 2053,
+    "composer3": 2054,
+    "composer4": 2055,
+    "composer5": 2056,
+    "composer6": 2057,
+    "composer7": 2058,
+    "composer8": 2059,
+    "composer9": 2060,
+    "composer10": 2061,
+    "composer11": 2062,
+    "composer12": 2063,
+    "composer13": 2064,
+    "composer14": 2065,
+    "composer15": 2066,
+    "composer16": 2067,
+    "composer17": 2068,
+    "composer18": 2069,
+    "composer19": 2070,
+    "composer20": 2071,
+    "composer21": 2072
+  }
+}

preprocessor_config.json

@@ -3,14 +3,17 @@
   "start_token_id": 0,
   "target_length": 256,
   "input_length": 1024,
-  "n_bars": 2,
+  "num_bars": 2,
   "sampling_rate": 22050,
-  "use_mel": true,
   "mel_is_conditioned": true,
   "padding_value": 0,
   "eos_token_id": 1,
   "vocab_size_special": 4,
   "vocab_size_note": 128,
   "vocab_size_velocity": 2,
-  "vocab_size_time": 100
+  "vocab_size_time": 100,
+  "window_size":4096,
+  "hop_length":1024,
+  "min_frequency":10.0,
+  "feature_size":512
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:922e69a8b08e20231ea8c4e47cfe53c6854e78951938c4e9e74e5f16f43b101a
-size 240697027
+oid sha256:4ebff90f182961d1dc7c8cf481289b5c926610fe89993b5b02f1a61fb29dfa45
+size 236483933

tokenizer_config.json

@@ -0,0 +1,8 @@
+{
+  "tokenizer_class": "Pop2PianoTokenizer",
+  "vocab_size_special" : 4,
+  "vocab_size_note" : 128,
+  "vocab_size_velocity" : 2,
+  "vocab_size_time" : 100,
+  "num_bars" : 2 
+}