Binbariyon
commited on
Commit
•
7ef6907
1
Parent(s):
89d337d
End of training
Browse files- README.md +62 -0
- config.json +104 -4
- generation_config.json +3 -11
- model.safetensors +1 -1
- runs/Jul22_07-38-28_522c13c980b4/events.out.tfevents.1721633978.522c13c980b4.769.0 +3 -0
- runs/Jul22_07-46-56_522c13c980b4/events.out.tfevents.1721634434.522c13c980b4.769.1 +3 -0
- runs/Jul22_07-53-49_522c13c980b4/events.out.tfevents.1721634843.522c13c980b4.769.2 +3 -0
- runs/Jul22_08-37-45_522c13c980b4/events.out.tfevents.1721637492.522c13c980b4.769.3 +3 -0
- runs/Jul22_08-41-09_522c13c980b4/events.out.tfevents.1721637696.522c13c980b4.769.4 +3 -0
- runs/Jul22_08-44-26_522c13c980b4/events.out.tfevents.1721637897.522c13c980b4.769.5 +3 -0
- runs/Jul22_08-49-21_522c13c980b4/events.out.tfevents.1721638185.522c13c980b4.769.6 +3 -0
- training_args.bin +2 -2
README.md
ADDED
@@ -0,0 +1,62 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
language:
|
3 |
+
- tr
|
4 |
+
license: apache-2.0
|
5 |
+
base_model: openai/whisper-small
|
6 |
+
tags:
|
7 |
+
- generated_from_trainer
|
8 |
+
datasets:
|
9 |
+
- mozilla-foundation/common_voice_17_0
|
10 |
+
model-index:
|
11 |
+
- name: Whisper Small Tr - Enes Akman
|
12 |
+
results: []
|
13 |
+
---
|
14 |
+
|
15 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
16 |
+
should probably proofread and complete it, then remove this comment. -->
|
17 |
+
|
18 |
+
# Whisper Small Tr - Enes Akman
|
19 |
+
|
20 |
+
This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the Common Voice 17.0 dataset.
|
21 |
+
It achieves the following results on the evaluation set:
|
22 |
+
- eval_loss: 0.2929
|
23 |
+
- eval_wer: 23.1615
|
24 |
+
- eval_runtime: 568.3304
|
25 |
+
- eval_samples_per_second: 3.519
|
26 |
+
- eval_steps_per_second: 0.07
|
27 |
+
- epoch: 3.0
|
28 |
+
- step: 180
|
29 |
+
|
30 |
+
## Model description
|
31 |
+
|
32 |
+
More information needed
|
33 |
+
|
34 |
+
## Intended uses & limitations
|
35 |
+
|
36 |
+
More information needed
|
37 |
+
|
38 |
+
## Training and evaluation data
|
39 |
+
|
40 |
+
More information needed
|
41 |
+
|
42 |
+
## Training procedure
|
43 |
+
|
44 |
+
### Training hyperparameters
|
45 |
+
|
46 |
+
The following hyperparameters were used during training:
|
47 |
+
- learning_rate: 1e-05
|
48 |
+
- train_batch_size: 100
|
49 |
+
- eval_batch_size: 50
|
50 |
+
- seed: 42
|
51 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
52 |
+
- lr_scheduler_type: linear
|
53 |
+
- lr_scheduler_warmup_steps: 50
|
54 |
+
- training_steps: 600
|
55 |
+
- mixed_precision_training: Native AMP
|
56 |
+
|
57 |
+
### Framework versions
|
58 |
+
|
59 |
+
- Transformers 4.42.4
|
60 |
+
- Pytorch 2.3.1+cu121
|
61 |
+
- Datasets 2.20.0
|
62 |
+
- Tokenizers 0.19.1
|
config.json
CHANGED
@@ -25,7 +25,20 @@
|
|
25 |
"encoder_layerdrop": 0.0,
|
26 |
"encoder_layers": 12,
|
27 |
"eos_token_id": 50257,
|
28 |
-
"forced_decoder_ids":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
29 |
"init_std": 0.02,
|
30 |
"is_encoder_decoder": true,
|
31 |
"mask_feature_length": 10,
|
@@ -43,10 +56,97 @@
|
|
43 |
"num_mel_bins": 80,
|
44 |
"pad_token_id": 50257,
|
45 |
"scale_embedding": false,
|
46 |
-
"suppress_tokens": [
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
47 |
"torch_dtype": "float32",
|
48 |
-
"transformers_version": "4.
|
49 |
-
"use_cache":
|
50 |
"use_weighted_layer_sum": false,
|
51 |
"vocab_size": 51865
|
52 |
}
|
|
|
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 |
"init_std": 0.02,
|
43 |
"is_encoder_decoder": true,
|
44 |
"mask_feature_length": 10,
|
|
|
56 |
"num_mel_bins": 80,
|
57 |
"pad_token_id": 50257,
|
58 |
"scale_embedding": false,
|
59 |
+
"suppress_tokens": [
|
60 |
+
1,
|
61 |
+
2,
|
62 |
+
7,
|
63 |
+
8,
|
64 |
+
9,
|
65 |
+
10,
|
66 |
+
14,
|
67 |
+
25,
|
68 |
+
26,
|
69 |
+
27,
|
70 |
+
28,
|
71 |
+
29,
|
72 |
+
31,
|
73 |
+
58,
|
74 |
+
59,
|
75 |
+
60,
|
76 |
+
61,
|
77 |
+
62,
|
78 |
+
63,
|
79 |
+
90,
|
80 |
+
91,
|
81 |
+
92,
|
82 |
+
93,
|
83 |
+
359,
|
84 |
+
503,
|
85 |
+
522,
|
86 |
+
542,
|
87 |
+
873,
|
88 |
+
893,
|
89 |
+
902,
|
90 |
+
918,
|
91 |
+
922,
|
92 |
+
931,
|
93 |
+
1350,
|
94 |
+
1853,
|
95 |
+
1982,
|
96 |
+
2460,
|
97 |
+
2627,
|
98 |
+
3246,
|
99 |
+
3253,
|
100 |
+
3268,
|
101 |
+
3536,
|
102 |
+
3846,
|
103 |
+
3961,
|
104 |
+
4183,
|
105 |
+
4667,
|
106 |
+
6585,
|
107 |
+
6647,
|
108 |
+
7273,
|
109 |
+
9061,
|
110 |
+
9383,
|
111 |
+
10428,
|
112 |
+
10929,
|
113 |
+
11938,
|
114 |
+
12033,
|
115 |
+
12331,
|
116 |
+
12562,
|
117 |
+
13793,
|
118 |
+
14157,
|
119 |
+
14635,
|
120 |
+
15265,
|
121 |
+
15618,
|
122 |
+
16553,
|
123 |
+
16604,
|
124 |
+
18362,
|
125 |
+
18956,
|
126 |
+
20075,
|
127 |
+
21675,
|
128 |
+
22520,
|
129 |
+
26130,
|
130 |
+
26161,
|
131 |
+
26435,
|
132 |
+
28279,
|
133 |
+
29464,
|
134 |
+
31650,
|
135 |
+
32302,
|
136 |
+
32470,
|
137 |
+
36865,
|
138 |
+
42863,
|
139 |
+
47425,
|
140 |
+
49870,
|
141 |
+
50254,
|
142 |
+
50258,
|
143 |
+
50360,
|
144 |
+
50361,
|
145 |
+
50362
|
146 |
+
],
|
147 |
"torch_dtype": "float32",
|
148 |
+
"transformers_version": "4.42.4",
|
149 |
+
"use_cache": true,
|
150 |
"use_weighted_layer_sum": false,
|
151 |
"vocab_size": 51865
|
152 |
}
|
generation_config.json
CHANGED
@@ -48,16 +48,6 @@
|
|
48 |
"bos_token_id": 50257,
|
49 |
"decoder_start_token_id": 50258,
|
50 |
"eos_token_id": 50257,
|
51 |
-
"forced_decoder_ids": [
|
52 |
-
[
|
53 |
-
1,
|
54 |
-
null
|
55 |
-
],
|
56 |
-
[
|
57 |
-
2,
|
58 |
-
50359
|
59 |
-
]
|
60 |
-
],
|
61 |
"is_multilingual": true,
|
62 |
"lang_to_id": {
|
63 |
"<|af|>": 50327,
|
@@ -160,6 +150,7 @@
|
|
160 |
"<|yo|>": 50325,
|
161 |
"<|zh|>": 50260
|
162 |
},
|
|
|
163 |
"max_initial_timestamp_index": 50,
|
164 |
"max_length": 448,
|
165 |
"no_timestamps_token_id": 50363,
|
@@ -256,9 +247,10 @@
|
|
256 |
50361,
|
257 |
50362
|
258 |
],
|
|
|
259 |
"task_to_id": {
|
260 |
"transcribe": 50359,
|
261 |
"translate": 50358
|
262 |
},
|
263 |
-
"transformers_version": "4.
|
264 |
}
|
|
|
48 |
"bos_token_id": 50257,
|
49 |
"decoder_start_token_id": 50258,
|
50 |
"eos_token_id": 50257,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
51 |
"is_multilingual": true,
|
52 |
"lang_to_id": {
|
53 |
"<|af|>": 50327,
|
|
|
150 |
"<|yo|>": 50325,
|
151 |
"<|zh|>": 50260
|
152 |
},
|
153 |
+
"language": "turkish",
|
154 |
"max_initial_timestamp_index": 50,
|
155 |
"max_length": 448,
|
156 |
"no_timestamps_token_id": 50363,
|
|
|
247 |
50361,
|
248 |
50362
|
249 |
],
|
250 |
+
"task": "transcribe",
|
251 |
"task_to_id": {
|
252 |
"transcribe": 50359,
|
253 |
"translate": 50358
|
254 |
},
|
255 |
+
"transformers_version": "4.42.4"
|
256 |
}
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 966995080
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c26ae1bbc57fe5e7f84810212def1499cfd22c01c55bef9fd87df055caf85e57
|
3 |
size 966995080
|
runs/Jul22_07-38-28_522c13c980b4/events.out.tfevents.1721633978.522c13c980b4.769.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8b7b952dd688990837b3bc60d8f14dc7d7b5cab03ba1c51f4415f5b84882fbe6
|
3 |
+
size 6609
|
runs/Jul22_07-46-56_522c13c980b4/events.out.tfevents.1721634434.522c13c980b4.769.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4649f02394d1669e77f37fd98116afe4714ece7421323ddddf192a55d7cc2166
|
3 |
+
size 6810
|
runs/Jul22_07-53-49_522c13c980b4/events.out.tfevents.1721634843.522c13c980b4.769.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6f66005c19c4f53d8e11610f235d563a7515eea33c4df3bf94bec33f5172a283
|
3 |
+
size 11830
|
runs/Jul22_08-37-45_522c13c980b4/events.out.tfevents.1721637492.522c13c980b4.769.3
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b4313c21d5520d3326d6fd150a2425c96bfe4b1923e4703822d06c0fa1446599
|
3 |
+
size 6609
|
runs/Jul22_08-41-09_522c13c980b4/events.out.tfevents.1721637696.522c13c980b4.769.4
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c19ca1641fd769c82b88ddcb942d46a17a35e6b911ef3b35021a2edeb86e3173
|
3 |
+
size 6610
|
runs/Jul22_08-44-26_522c13c980b4/events.out.tfevents.1721637897.522c13c980b4.769.5
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a0fa6c06e0221f4effb6062852a9f76e6968c19bcf934465e421c840dfe8ea49
|
3 |
+
size 13126
|
runs/Jul22_08-49-21_522c13c980b4/events.out.tfevents.1721638185.522c13c980b4.769.6
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f3631f3849a5d2ee32184bb344a22409591b564b7abcce277050759c10f00825
|
3 |
+
size 11510
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1858b0905220914c8ea2f22c27c82d3279c2c4da294699a5f6a484450d04aeec
|
3 |
+
size 5240
|