Image-to-Text
Transformers
Safetensors
English
SMT
text-generation
optical-music-recognition
music-transcription
jazz
lead-sheets
kern
sheet-music-transformer
Instructions to use JuanCarlosMartinezSevilla/jazzmus-model with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use JuanCarlosMartinezSevilla/jazzmus-model with Transformers:
# Use a pipeline as a high-level helper # Warning: Pipeline type "image-to-text" is no longer supported in transformers v5. # You must load the model directly (see below) or downgrade to v4.x with: # 'pip install "transformers<5.0.0' from transformers import pipeline pipe = pipeline("image-to-text", model="JuanCarlosMartinezSevilla/jazzmus-model")# Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("JuanCarlosMartinezSevilla/jazzmus-model", dtype="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "architectures": [ | |
| "SMTModelForCausalLM" | |
| ], | |
| "d_model": 256, | |
| "dim_ff": 256, | |
| "dtype": "float32", | |
| "enc_depths": [ | |
| 3, | |
| 3, | |
| 9 | |
| ], | |
| "enc_stages": 3, | |
| "hidden_enc_sizes": [ | |
| 64, | |
| 128, | |
| 256 | |
| ], | |
| "i2w": { | |
| "0": "<pad>", | |
| "1": "<chord-extension>11", | |
| "2": "*k[b-e-a-d-g-c-]", | |
| "3": "6", | |
| "4": "F", | |
| "5": "*c:", | |
| "6": "maj", | |
| "7": "<chord-pitch>Eb", | |
| "8": "aug", | |
| "9": "*B-:", | |
| "10": "*", | |
| "11": "_", | |
| "12": "g", | |
| "13": "<chord-pitch>Bb", | |
| "14": "G", | |
| "15": "3", | |
| "16": "gg", | |
| "17": "*k[]", | |
| "18": "B", | |
| "19": "<chord-pitch>B", | |
| "20": "*MM80", | |
| "21": "<chord-extension>7", | |
| "22": "a", | |
| "23": "11", | |
| "24": ":", | |
| "25": "L", | |
| "26": "aa", | |
| "27": "c", | |
| "28": "*k[b-]", | |
| "29": "9", | |
| "30": "C", | |
| "31": "<chord-pitch>E", | |
| "32": "*M2/4", | |
| "33": "*Trd0c0", | |
| "34": "*k[b-e-]", | |
| "35": "<chord-extension>6", | |
| "36": "E", | |
| "37": "*MM120", | |
| "38": "min7", | |
| "39": "]", | |
| "40": "<n>", | |
| "41": "*E-:", | |
| "42": "~", | |
| "43": "*M2/2", | |
| "44": "*M3/4", | |
| "45": "f", | |
| "46": "*MM150", | |
| "47": "*clefF4", | |
| "48": "*^", | |
| "49": "d", | |
| "50": "<chord-extension>no5", | |
| "51": "*met(c)", | |
| "52": "*G-:", | |
| "53": "=!|:", | |
| "54": ".", | |
| "55": "cc", | |
| "56": "eee", | |
| "57": "*e-:", | |
| "58": "BB", | |
| "59": "<chord-pitch>Db", | |
| "60": "*k[f#c#g#d#a#]", | |
| "61": "*k[b-e-a-d-]", | |
| "62": "*G:", | |
| "63": "D", | |
| "64": "=||", | |
| "65": "<chord-pitch>C", | |
| "66": "min11", | |
| "67": "k", | |
| "68": "0", | |
| "69": "<chord-pitch>A", | |
| "70": "ddd", | |
| "71": "<chord-extension>9", | |
| "72": "**mxhm", | |
| "73": "n", | |
| "74": "<chord-pitch>Ab", | |
| "75": "<chord-pitch>Gb", | |
| "76": "<chord-pitch>Fb", | |
| "77": "J", | |
| "78": "/", | |
| "79": " ", | |
| "80": "M", | |
| "81": "<chord-pitch>F", | |
| "82": "=:|!|:", | |
| "83": "4", | |
| "84": "min6", | |
| "85": "==", | |
| "86": "aug7", | |
| "87": "<eos>", | |
| "88": "*MM240", | |
| "89": "=", | |
| "90": "y", | |
| "91": "*k[b-e-a-d-g-]", | |
| "92": "min", | |
| "93": "*d:", | |
| "94": "K", | |
| "95": "*D-:", | |
| "96": "*M4/4", | |
| "97": "*k[f#]", | |
| "98": "<chord-extension>13", | |
| "99": "*clefG2", | |
| "100": ")", | |
| "101": "<chord-pitch>Cb", | |
| "102": "^", | |
| "103": "*D:", | |
| "104": "'", | |
| "105": "<bos>", | |
| "106": "*A-:", | |
| "107": "<chord-pitch>G", | |
| "108": "8", | |
| "109": "b", | |
| "110": "maj6", | |
| "111": "=:|!", | |
| "112": "r", | |
| "113": "dd", | |
| "114": "13", | |
| "115": "<chord-pitch>D", | |
| "116": "ccc", | |
| "117": "*M5/4", | |
| "118": "-", | |
| "119": ",", | |
| "120": "dim", | |
| "121": "*met(c|)", | |
| "122": "7", | |
| "123": "minmaj7", | |
| "124": "*v", | |
| "125": "A", | |
| "126": "(", | |
| "127": "dim7", | |
| "128": "*MM96", | |
| "129": "*k[f#c#]", | |
| "130": "e", | |
| "131": "<t>", | |
| "132": "none", | |
| "133": "[", | |
| "134": "1", | |
| "135": "i", | |
| "136": "[8dd", | |
| "137": "bb", | |
| "138": "#", | |
| "139": "*MM200", | |
| "140": "2", | |
| "141": "**kern", | |
| "142": "maj7", | |
| "143": "*k[b-e-a-]", | |
| "144": ";", | |
| "145": "maj9", | |
| "146": "<chord-extension>5", | |
| "147": "ee", | |
| "148": "min9", | |
| "149": "*B:", | |
| "150": "hdim7", | |
| "151": "sus4", | |
| "152": "ff" | |
| }, | |
| "in_channels": 1, | |
| "maxh": 128, | |
| "maxlen": 277, | |
| "maxw": 1000, | |
| "model_type": "SMT", | |
| "num_attn_heads": 4, | |
| "num_dec_layers": 8, | |
| "out_categories": 153, | |
| "out_dir": "out_smt", | |
| "padding_token": 0, | |
| "transformers_version": "5.3.0", | |
| "use_flash_attn": false, | |
| "w2i": { | |
| " ": 79, | |
| "#": 138, | |
| "'": 104, | |
| "(": 126, | |
| ")": 100, | |
| "*": 10, | |
| "**kern": 141, | |
| "**mxhm": 72, | |
| "*A-:": 106, | |
| "*B-:": 9, | |
| "*B:": 149, | |
| "*D-:": 95, | |
| "*D:": 103, | |
| "*E-:": 41, | |
| "*G-:": 52, | |
| "*G:": 62, | |
| "*M2/2": 43, | |
| "*M2/4": 32, | |
| "*M3/4": 44, | |
| "*M4/4": 96, | |
| "*M5/4": 117, | |
| "*MM120": 37, | |
| "*MM150": 46, | |
| "*MM200": 139, | |
| "*MM240": 88, | |
| "*MM80": 20, | |
| "*MM96": 128, | |
| "*Trd0c0": 33, | |
| "*^": 48, | |
| "*c:": 5, | |
| "*clefF4": 47, | |
| "*clefG2": 99, | |
| "*d:": 93, | |
| "*e-:": 57, | |
| "*k[]": 17, | |
| "*k[b-]": 28, | |
| "*k[b-e-]": 34, | |
| "*k[b-e-a-]": 143, | |
| "*k[b-e-a-d-]": 61, | |
| "*k[b-e-a-d-g-]": 91, | |
| "*k[b-e-a-d-g-c-]": 2, | |
| "*k[f#]": 97, | |
| "*k[f#c#]": 129, | |
| "*k[f#c#g#d#a#]": 60, | |
| "*met(c)": 51, | |
| "*met(c|)": 121, | |
| "*v": 124, | |
| ",": 119, | |
| "-": 118, | |
| ".": 54, | |
| "/": 78, | |
| "0": 68, | |
| "1": 134, | |
| "11": 23, | |
| "13": 114, | |
| "2": 140, | |
| "3": 15, | |
| "4": 83, | |
| "6": 3, | |
| "7": 122, | |
| "8": 108, | |
| "9": 29, | |
| ":": 24, | |
| ";": 144, | |
| "<bos>": 105, | |
| "<chord-extension>11": 1, | |
| "<chord-extension>13": 98, | |
| "<chord-extension>5": 146, | |
| "<chord-extension>6": 35, | |
| "<chord-extension>7": 21, | |
| "<chord-extension>9": 71, | |
| "<chord-extension>no5": 50, | |
| "<chord-pitch>A": 69, | |
| "<chord-pitch>Ab": 74, | |
| "<chord-pitch>B": 19, | |
| "<chord-pitch>Bb": 13, | |
| "<chord-pitch>C": 65, | |
| "<chord-pitch>Cb": 101, | |
| "<chord-pitch>D": 115, | |
| "<chord-pitch>Db": 59, | |
| "<chord-pitch>E": 31, | |
| "<chord-pitch>Eb": 7, | |
| "<chord-pitch>F": 81, | |
| "<chord-pitch>Fb": 76, | |
| "<chord-pitch>G": 107, | |
| "<chord-pitch>Gb": 75, | |
| "<eos>": 87, | |
| "<n>": 40, | |
| "<pad>": 0, | |
| "<t>": 131, | |
| "=": 89, | |
| "=!|:": 53, | |
| "=:|!": 111, | |
| "=:|!|:": 82, | |
| "==": 85, | |
| "=||": 64, | |
| "A": 125, | |
| "B": 18, | |
| "BB": 58, | |
| "C": 30, | |
| "D": 63, | |
| "E": 36, | |
| "F": 4, | |
| "G": 14, | |
| "J": 77, | |
| "K": 94, | |
| "L": 25, | |
| "M": 80, | |
| "[": 133, | |
| "[8dd": 136, | |
| "]": 39, | |
| "^": 102, | |
| "_": 11, | |
| "a": 22, | |
| "aa": 26, | |
| "aug": 8, | |
| "aug7": 86, | |
| "b": 109, | |
| "bb": 137, | |
| "c": 27, | |
| "cc": 55, | |
| "ccc": 116, | |
| "d": 49, | |
| "dd": 113, | |
| "ddd": 70, | |
| "dim": 120, | |
| "dim7": 127, | |
| "e": 130, | |
| "ee": 147, | |
| "eee": 56, | |
| "f": 45, | |
| "ff": 152, | |
| "g": 12, | |
| "gg": 16, | |
| "hdim7": 150, | |
| "i": 135, | |
| "k": 67, | |
| "maj": 6, | |
| "maj6": 110, | |
| "maj7": 142, | |
| "maj9": 145, | |
| "min": 92, | |
| "min11": 66, | |
| "min6": 84, | |
| "min7": 38, | |
| "min9": 148, | |
| "minmaj7": 123, | |
| "n": 73, | |
| "none": 132, | |
| "r": 112, | |
| "sus4": 151, | |
| "y": 90, | |
| "~": 42 | |
| } | |
| } | |