juancopi81
commited on
Commit
·
f680768
1
Parent(s):
44abe18
Training in progress epoch 0
Browse files- README.md +20 -37
- config.json +1 -1
- tf_model.h5 +1 -1
README.md
CHANGED
@@ -1,69 +1,52 @@
|
|
1 |
---
|
2 |
tags:
|
3 |
- generated_from_keras_callback
|
4 |
-
- music
|
5 |
model-index:
|
6 |
- name: juancopi81/mutopia_guitar_mmm
|
7 |
results: []
|
8 |
-
datasets:
|
9 |
-
- juancopi81/mutopia_guitar_dataset
|
10 |
-
widget:
|
11 |
-
- text: "PIECE_START TIME_SIGNATURE=4_4 BPM=90 TRACK_START INST=0 DENSITY=2 BAR_START NOTE_ON=43"
|
12 |
-
example_title: "Time signature 4/4, BPM=90, NOTE=G2"
|
13 |
---
|
14 |
|
15 |
-
|
16 |
-
|
17 |
-
Music generation could be approached similarly to language generation. There are many ways to represent music as text and then use a language model to create a model capable of music generation. For encoding MIDI files as text, I am using the excellent [implementation](https://github.com/AI-Guru/MMM-JSB) of Dr. Tristan Beheren of the paper: [MMM: Exploring Conditional Multi-Track Music Generation with the Transformer](https://arxiv.org/abs/2008.06048).
|
18 |
|
19 |
-
|
20 |
-
I created the notebook as an adaptation of [the one created by Dr. Tristan Behrens](https://huggingface.co/TristanBehrens/js-fakes-4bars).
|
21 |
|
|
|
22 |
It achieves the following results on the evaluation set:
|
23 |
-
- Train Loss: 0.
|
24 |
-
- Validation Loss: 1.
|
|
|
25 |
|
26 |
## Model description
|
27 |
|
28 |
-
|
29 |
-
`WhitespaceSplit` pre-tokenizer. The [tokenizer](https://huggingface.co/juancopi81/mutopia_guitar_dataset_tokenizer) is also in the Hugging Face hub.
|
30 |
|
31 |
## Intended uses & limitations
|
32 |
|
33 |
-
|
34 |
-
The main intention of this model is educational. I am creating a [series of notebooks](https://github.com/juancopi81/MMM_Mutopia_Guitar) where I show every step of the process:
|
35 |
-
- Collecting the data
|
36 |
-
- Pre-processing the data
|
37 |
-
- Training a tokenizer from scratch
|
38 |
-
- Fine-tuning a GPT-2 model
|
39 |
-
- Building a Gradio app for the model
|
40 |
-
|
41 |
-
I trained the model using the free version of Colab with a small dataset. Right now, it is heavily overfitting. My idea is to have a more extensive dataset of Guitar Music from Latinoamerica to train a new model similar to the Mutopia Guitar Model, using more GPU resources.
|
42 |
|
43 |
## Training and evaluation data
|
44 |
|
45 |
-
|
46 |
-
|
|
|
47 |
|
48 |
### Training hyperparameters
|
49 |
|
50 |
The following hyperparameters were used during training:
|
51 |
-
- optimizer: {'name': 'AdamWeightDecay', 'learning_rate': {'class_name': 'WarmUp', 'config': {'initial_learning_rate': 5e-
|
52 |
- training_precision: mixed_float16
|
|
|
53 |
### Training results
|
|
|
54 |
| Train Loss | Validation Loss | Epoch |
|
55 |
|:----------:|:---------------:|:-----:|
|
56 |
-
|
|
57 |
-
|
58 |
-
| 0.7588 | 1.3974 | 2 |
|
59 |
-
| 0.7294 | 1.4813 | 3 |
|
60 |
-
| 0.6263 | 1.5263 | 5 |
|
61 |
-
| 0.5841 | 1.5263 | 6 |
|
62 |
-
| 0.5844 | 1.5263 | 7 |
|
63 |
-
| 0.5837 | 1.5346 | 8 |
|
64 |
|
65 |
### Framework versions
|
66 |
-
|
|
|
67 |
- TensorFlow 2.8.2
|
68 |
-
- Datasets 2.
|
69 |
- Tokenizers 0.12.1
|
|
|
1 |
---
|
2 |
tags:
|
3 |
- generated_from_keras_callback
|
|
|
4 |
model-index:
|
5 |
- name: juancopi81/mutopia_guitar_mmm
|
6 |
results: []
|
|
|
|
|
|
|
|
|
|
|
7 |
---
|
8 |
|
9 |
+
<!-- This model card has been generated automatically according to the information Keras had access to. You should
|
10 |
+
probably proofread and complete it, then remove this comment. -->
|
|
|
11 |
|
12 |
+
# juancopi81/mutopia_guitar_mmm
|
|
|
13 |
|
14 |
+
This model was trained from scratch on an unknown dataset.
|
15 |
It achieves the following results on the evaluation set:
|
16 |
+
- Train Loss: 0.5798
|
17 |
+
- Validation Loss: 1.5411
|
18 |
+
- Epoch: 0
|
19 |
|
20 |
## Model description
|
21 |
|
22 |
+
More information needed
|
|
|
23 |
|
24 |
## Intended uses & limitations
|
25 |
|
26 |
+
More information needed
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
27 |
|
28 |
## Training and evaluation data
|
29 |
|
30 |
+
More information needed
|
31 |
+
|
32 |
+
## Training procedure
|
33 |
|
34 |
### Training hyperparameters
|
35 |
|
36 |
The following hyperparameters were used during training:
|
37 |
+
- optimizer: {'name': 'AdamWeightDecay', 'learning_rate': {'class_name': 'WarmUp', 'config': {'initial_learning_rate': 5e-07, 'decay_schedule_fn': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 5e-07, 'decay_steps': 5726, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, '__passive_serialization__': True}, 'warmup_steps': 1000, 'power': 1.0, 'name': None}}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.01}
|
38 |
- training_precision: mixed_float16
|
39 |
+
|
40 |
### Training results
|
41 |
+
|
42 |
| Train Loss | Validation Loss | Epoch |
|
43 |
|:----------:|:---------------:|:-----:|
|
44 |
+
| 0.5798 | 1.5411 | 0 |
|
45 |
+
|
|
|
|
|
|
|
|
|
|
|
|
|
46 |
|
47 |
### Framework versions
|
48 |
+
|
49 |
+
- Transformers 4.22.1
|
50 |
- TensorFlow 2.8.2
|
51 |
+
- Datasets 2.5.1
|
52 |
- Tokenizers 0.12.1
|
config.json
CHANGED
@@ -32,7 +32,7 @@
|
|
32 |
"max_length": 350
|
33 |
}
|
34 |
},
|
35 |
-
"transformers_version": "4.22.
|
36 |
"use_cache": true,
|
37 |
"vocab_size": 588
|
38 |
}
|
|
|
32 |
"max_length": 350
|
33 |
}
|
34 |
},
|
35 |
+
"transformers_version": "4.22.1",
|
36 |
"use_cache": true,
|
37 |
"vocab_size": 588
|
38 |
}
|
tf_model.h5
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 345352296
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3d5d509dbdd6d95998211d5f6f22a7c6e94e85021d3dc6a3c31f5fb690a0da8a
|
3 |
size 345352296
|