Aynursusuz/whisper_small
Browse files- README.md +5 -5
- config.json +77 -73
- model.safetensors +1 -1
- training_args.bin +1 -1
README.md
CHANGED
|
@@ -1,7 +1,7 @@
|
|
| 1 |
---
|
| 2 |
library_name: transformers
|
| 3 |
-
license:
|
| 4 |
-
base_model:
|
| 5 |
tags:
|
| 6 |
- generated_from_trainer
|
| 7 |
metrics:
|
|
@@ -16,9 +16,9 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 16 |
|
| 17 |
# music_speech_classification
|
| 18 |
|
| 19 |
-
This model is a fine-tuned version of [
|
| 20 |
It achieves the following results on the evaluation set:
|
| 21 |
-
- Loss: 0.
|
| 22 |
- Accuracy: 1.0
|
| 23 |
|
| 24 |
## Model description
|
|
@@ -54,7 +54,7 @@ The following hyperparameters were used during training:
|
|
| 54 |
|
| 55 |
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 56 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
| 57 |
-
| 0.
|
| 58 |
|
| 59 |
|
| 60 |
### Framework versions
|
|
|
|
| 1 |
---
|
| 2 |
library_name: transformers
|
| 3 |
+
license: apache-2.0
|
| 4 |
+
base_model: openai/whisper-small
|
| 5 |
tags:
|
| 6 |
- generated_from_trainer
|
| 7 |
metrics:
|
|
|
|
| 16 |
|
| 17 |
# music_speech_classification
|
| 18 |
|
| 19 |
+
This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on an unknown dataset.
|
| 20 |
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: 0.0001
|
| 22 |
- Accuracy: 1.0
|
| 23 |
|
| 24 |
## Model description
|
|
|
|
| 54 |
|
| 55 |
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 56 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
| 57 |
+
| 0.0 | 1.0 | 287 | 0.0001 | 1.0 |
|
| 58 |
|
| 59 |
|
| 60 |
### Framework versions
|
config.json
CHANGED
|
@@ -8,7 +8,7 @@
|
|
| 8 |
"attention_dropout": 0.0,
|
| 9 |
"begin_suppress_tokens": [
|
| 10 |
220,
|
| 11 |
-
|
| 12 |
],
|
| 13 |
"bos_token_id": 50257,
|
| 14 |
"classifier_proj_size": 256,
|
|
@@ -16,19 +16,27 @@
|
|
| 16 |
"decoder_attention_heads": 12,
|
| 17 |
"decoder_ffn_dim": 3072,
|
| 18 |
"decoder_layerdrop": 0.0,
|
| 19 |
-
"decoder_layers":
|
| 20 |
-
"decoder_start_token_id":
|
| 21 |
"dropout": 0.0,
|
| 22 |
"dtype": "float32",
|
| 23 |
"encoder_attention_heads": 12,
|
| 24 |
"encoder_ffn_dim": 3072,
|
| 25 |
"encoder_layerdrop": 0.0,
|
| 26 |
"encoder_layers": 12,
|
| 27 |
-
"eos_token_id":
|
| 28 |
"forced_decoder_ids": [
|
| 29 |
[
|
| 30 |
1,
|
| 31 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 32 |
]
|
| 33 |
],
|
| 34 |
"id2label": {
|
|
@@ -54,7 +62,7 @@
|
|
| 54 |
"model_type": "whisper",
|
| 55 |
"num_hidden_layers": 12,
|
| 56 |
"num_mel_bins": 80,
|
| 57 |
-
"pad_token_id":
|
| 58 |
"scale_embedding": false,
|
| 59 |
"suppress_tokens": [
|
| 60 |
1,
|
|
@@ -80,76 +88,72 @@
|
|
| 80 |
91,
|
| 81 |
92,
|
| 82 |
93,
|
| 83 |
-
|
| 84 |
-
|
| 85 |
-
|
| 86 |
-
|
| 87 |
-
|
| 88 |
-
|
| 89 |
-
|
| 90 |
-
|
| 91 |
-
|
| 92 |
-
|
| 93 |
-
|
| 94 |
-
|
| 95 |
-
|
| 96 |
-
|
| 97 |
-
|
| 98 |
-
|
| 99 |
-
|
| 100 |
-
|
| 101 |
-
|
| 102 |
-
|
| 103 |
-
|
| 104 |
-
|
| 105 |
-
|
| 106 |
-
|
| 107 |
-
|
| 108 |
-
|
| 109 |
-
|
| 110 |
-
|
| 111 |
-
|
| 112 |
-
|
| 113 |
-
|
| 114 |
-
|
| 115 |
-
|
| 116 |
-
|
| 117 |
-
|
| 118 |
-
|
| 119 |
-
|
| 120 |
-
|
| 121 |
-
|
| 122 |
-
|
| 123 |
-
|
| 124 |
-
|
| 125 |
-
|
| 126 |
-
|
| 127 |
-
|
| 128 |
-
|
| 129 |
-
|
| 130 |
-
|
| 131 |
-
|
| 132 |
-
|
| 133 |
-
|
| 134 |
-
|
| 135 |
-
|
| 136 |
-
|
| 137 |
-
|
| 138 |
-
|
| 139 |
-
|
| 140 |
-
|
| 141 |
-
|
| 142 |
-
|
| 143 |
-
49146,
|
| 144 |
-
50257,
|
| 145 |
-
50357,
|
| 146 |
-
50358,
|
| 147 |
-
50359,
|
| 148 |
50360,
|
| 149 |
-
50361
|
|
|
|
| 150 |
],
|
| 151 |
"transformers_version": "4.57.1",
|
| 152 |
"use_cache": true,
|
| 153 |
"use_weighted_layer_sum": false,
|
| 154 |
-
"vocab_size":
|
| 155 |
}
|
|
|
|
| 8 |
"attention_dropout": 0.0,
|
| 9 |
"begin_suppress_tokens": [
|
| 10 |
220,
|
| 11 |
+
50257
|
| 12 |
],
|
| 13 |
"bos_token_id": 50257,
|
| 14 |
"classifier_proj_size": 256,
|
|
|
|
| 16 |
"decoder_attention_heads": 12,
|
| 17 |
"decoder_ffn_dim": 3072,
|
| 18 |
"decoder_layerdrop": 0.0,
|
| 19 |
+
"decoder_layers": 12,
|
| 20 |
+
"decoder_start_token_id": 50258,
|
| 21 |
"dropout": 0.0,
|
| 22 |
"dtype": "float32",
|
| 23 |
"encoder_attention_heads": 12,
|
| 24 |
"encoder_ffn_dim": 3072,
|
| 25 |
"encoder_layerdrop": 0.0,
|
| 26 |
"encoder_layers": 12,
|
| 27 |
+
"eos_token_id": 50257,
|
| 28 |
"forced_decoder_ids": [
|
| 29 |
[
|
| 30 |
1,
|
| 31 |
+
50259
|
| 32 |
+
],
|
| 33 |
+
[
|
| 34 |
+
2,
|
| 35 |
+
50359
|
| 36 |
+
],
|
| 37 |
+
[
|
| 38 |
+
3,
|
| 39 |
+
50363
|
| 40 |
]
|
| 41 |
],
|
| 42 |
"id2label": {
|
|
|
|
| 62 |
"model_type": "whisper",
|
| 63 |
"num_hidden_layers": 12,
|
| 64 |
"num_mel_bins": 80,
|
| 65 |
+
"pad_token_id": 50257,
|
| 66 |
"scale_embedding": false,
|
| 67 |
"suppress_tokens": [
|
| 68 |
1,
|
|
|
|
| 88 |
91,
|
| 89 |
92,
|
| 90 |
93,
|
| 91 |
+
359,
|
| 92 |
+
503,
|
| 93 |
+
522,
|
| 94 |
+
542,
|
| 95 |
+
873,
|
| 96 |
+
893,
|
| 97 |
+
902,
|
| 98 |
+
918,
|
| 99 |
+
922,
|
| 100 |
+
931,
|
| 101 |
+
1350,
|
| 102 |
+
1853,
|
| 103 |
+
1982,
|
| 104 |
+
2460,
|
| 105 |
+
2627,
|
| 106 |
+
3246,
|
| 107 |
+
3253,
|
| 108 |
+
3268,
|
| 109 |
+
3536,
|
| 110 |
+
3846,
|
| 111 |
+
3961,
|
| 112 |
+
4183,
|
| 113 |
+
4667,
|
| 114 |
+
6585,
|
| 115 |
+
6647,
|
| 116 |
+
7273,
|
| 117 |
+
9061,
|
| 118 |
+
9383,
|
| 119 |
+
10428,
|
| 120 |
+
10929,
|
| 121 |
+
11938,
|
| 122 |
+
12033,
|
| 123 |
+
12331,
|
| 124 |
+
12562,
|
| 125 |
+
13793,
|
| 126 |
+
14157,
|
| 127 |
+
14635,
|
| 128 |
+
15265,
|
| 129 |
+
15618,
|
| 130 |
+
16553,
|
| 131 |
+
16604,
|
| 132 |
+
18362,
|
| 133 |
+
18956,
|
| 134 |
+
20075,
|
| 135 |
+
21675,
|
| 136 |
+
22520,
|
| 137 |
+
26130,
|
| 138 |
+
26161,
|
| 139 |
+
26435,
|
| 140 |
+
28279,
|
| 141 |
+
29464,
|
| 142 |
+
31650,
|
| 143 |
+
32302,
|
| 144 |
+
32470,
|
| 145 |
+
36865,
|
| 146 |
+
42863,
|
| 147 |
+
47425,
|
| 148 |
+
49870,
|
| 149 |
+
50254,
|
| 150 |
+
50258,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 151 |
50360,
|
| 152 |
+
50361,
|
| 153 |
+
50362
|
| 154 |
],
|
| 155 |
"transformers_version": "4.57.1",
|
| 156 |
"use_cache": true,
|
| 157 |
"use_weighted_layer_sum": false,
|
| 158 |
+
"vocab_size": 51865
|
| 159 |
}
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 353426360
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:81ad8da8ce388a3cc615a3212f71eb205caf97303034d83d656ec15fc664cd13
|
| 3 |
size 353426360
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5969
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6f7d8a5b152aba59a1eb063ec20791eacd066e189de9144158f4a76e11ad7b07
|
| 3 |
size 5969
|