akmalmasud96
commited on
Commit
•
1cd05c0
1
Parent(s):
99cf47b
Training in progress, step 500
Browse files- README.md +9 -5
- added_tokens.json +4 -0
- all_results.json +14 -0
- eval_results.json +9 -0
- pytorch_model.bin +1 -1
- runs/Feb04_20-03-21_metis/events.out.tfevents.1675566712.metis.3870.2 +3 -0
- runs/Feb05_06-31-30_metis/1675578707.6084669/events.out.tfevents.1675578707.metis.52436.1 +3 -0
- runs/Feb05_06-31-30_metis/events.out.tfevents.1675578707.metis.52436.0 +3 -0
- special_tokens_map.json +22 -0
- tokenizer_config.json +13 -0
- train_results.json +8 -0
- trainer_state.json +0 -0
- training_args.bin +1 -1
- vocab.json +87 -0
README.md
CHANGED
@@ -1,5 +1,9 @@
|
|
1 |
---
|
|
|
|
|
2 |
tags:
|
|
|
|
|
3 |
- generated_from_trainer
|
4 |
datasets:
|
5 |
- common_voice_11_0
|
@@ -12,15 +16,15 @@ model-index:
|
|
12 |
name: Automatic Speech Recognition
|
13 |
type: automatic-speech-recognition
|
14 |
dataset:
|
15 |
-
name:
|
16 |
type: common_voice_11_0
|
17 |
config: ur
|
18 |
split: test
|
19 |
-
args: ur
|
20 |
metrics:
|
21 |
- name: Wer
|
22 |
type: wer
|
23 |
-
value: 0.
|
24 |
---
|
25 |
|
26 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
@@ -28,10 +32,10 @@ should probably proofread and complete it, then remove this comment. -->
|
|
28 |
|
29 |
# wavlm-common_voice-ur
|
30 |
|
31 |
-
This model is a fine-tuned version of [microsoft/wavlm-large](https://huggingface.co/microsoft/wavlm-large) on the
|
32 |
It achieves the following results on the evaluation set:
|
33 |
- Loss: inf
|
34 |
-
- Wer: 0.
|
35 |
|
36 |
## Model description
|
37 |
|
|
|
1 |
---
|
2 |
+
language:
|
3 |
+
- ur
|
4 |
tags:
|
5 |
+
- automatic-speech-recognition
|
6 |
+
- mozilla-foundation/common_voice_11_0
|
7 |
- generated_from_trainer
|
8 |
datasets:
|
9 |
- common_voice_11_0
|
|
|
16 |
name: Automatic Speech Recognition
|
17 |
type: automatic-speech-recognition
|
18 |
dataset:
|
19 |
+
name: MOZILLA-FOUNDATION/COMMON_VOICE_11_0 - UR
|
20 |
type: common_voice_11_0
|
21 |
config: ur
|
22 |
split: test
|
23 |
+
args: 'Config: ur, Training split: train+validation, Eval split: test'
|
24 |
metrics:
|
25 |
- name: Wer
|
26 |
type: wer
|
27 |
+
value: 0.37805822235986375
|
28 |
---
|
29 |
|
30 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
32 |
|
33 |
# wavlm-common_voice-ur
|
34 |
|
35 |
+
This model is a fine-tuned version of [microsoft/wavlm-large](https://huggingface.co/microsoft/wavlm-large) on the MOZILLA-FOUNDATION/COMMON_VOICE_11_0 - UR dataset.
|
36 |
It achieves the following results on the evaluation set:
|
37 |
- Loss: inf
|
38 |
+
- Wer: 0.3781
|
39 |
|
40 |
## Model description
|
41 |
|
added_tokens.json
ADDED
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"</s>": 86,
|
3 |
+
"<s>": 85
|
4 |
+
}
|
all_results.json
ADDED
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 15.0,
|
3 |
+
"eval_loss": Infinity,
|
4 |
+
"eval_runtime": 87.9288,
|
5 |
+
"eval_samples": 3302,
|
6 |
+
"eval_samples_per_second": 37.553,
|
7 |
+
"eval_steps_per_second": 2.354,
|
8 |
+
"eval_wer": 0.37805822235986375,
|
9 |
+
"train_loss": 0.4476442434369701,
|
10 |
+
"train_runtime": 25061.8442,
|
11 |
+
"train_samples": 7432,
|
12 |
+
"train_samples_per_second": 4.448,
|
13 |
+
"train_steps_per_second": 0.556
|
14 |
+
}
|
eval_results.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 15.0,
|
3 |
+
"eval_loss": Infinity,
|
4 |
+
"eval_runtime": 87.9288,
|
5 |
+
"eval_samples": 3302,
|
6 |
+
"eval_samples_per_second": 37.553,
|
7 |
+
"eval_steps_per_second": 2.354,
|
8 |
+
"eval_wer": 0.37805822235986375
|
9 |
+
}
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1262337525
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a827a3adabde47d22c52f1190fa9ec41178d8453cd00549e62e4912eb7cf01a3
|
3 |
size 1262337525
|
runs/Feb04_20-03-21_metis/events.out.tfevents.1675566712.metis.3870.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ed1a4a7d27a6298fa456d4e9bbf3e94d5ef0a715f377682467f63d2ea792e3a4
|
3 |
+
size 358
|
runs/Feb05_06-31-30_metis/1675578707.6084669/events.out.tfevents.1675578707.metis.52436.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:328ceaed19870934ae61f4785db09d105bcfb46fdbc699d7e32eeefe46d6557c
|
3 |
+
size 5762
|
runs/Feb05_06-31-30_metis/events.out.tfevents.1675578707.metis.52436.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:700a8bdd84dfb56fe7794d3e66ad30fcd44deda68dffce1ae39156f13ca8b350
|
3 |
+
size 84090
|
special_tokens_map.json
ADDED
@@ -0,0 +1,22 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
{
|
4 |
+
"content": "<s>",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": true,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false
|
9 |
+
},
|
10 |
+
{
|
11 |
+
"content": "</s>",
|
12 |
+
"lstrip": false,
|
13 |
+
"normalized": true,
|
14 |
+
"rstrip": false,
|
15 |
+
"single_word": false
|
16 |
+
}
|
17 |
+
],
|
18 |
+
"bos_token": "<s>",
|
19 |
+
"eos_token": "</s>",
|
20 |
+
"pad_token": "[PAD]",
|
21 |
+
"unk_token": "[UNK]"
|
22 |
+
}
|
tokenizer_config.json
ADDED
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<s>",
|
3 |
+
"do_lower_case": false,
|
4 |
+
"eos_token": "</s>",
|
5 |
+
"model_max_length": 1000000000000000019884624838656,
|
6 |
+
"name_or_path": "./wavlm-common_voice-ur",
|
7 |
+
"pad_token": "[PAD]",
|
8 |
+
"replace_word_delimiter_char": " ",
|
9 |
+
"special_tokens_map_file": null,
|
10 |
+
"tokenizer_class": "Wav2Vec2CTCTokenizer",
|
11 |
+
"unk_token": "[UNK]",
|
12 |
+
"word_delimiter_token": "|"
|
13 |
+
}
|
train_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 15.0,
|
3 |
+
"train_loss": 0.4476442434369701,
|
4 |
+
"train_runtime": 25061.8442,
|
5 |
+
"train_samples": 7432,
|
6 |
+
"train_samples_per_second": 4.448,
|
7 |
+
"train_steps_per_second": 0.556
|
8 |
+
}
|
trainer_state.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 3515
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bbe193ce9901f1e5597c8470cfd51ecd318fc8106a6138a23fb7aae4fc5405d9
|
3 |
size 3515
|
vocab.json
ADDED
@@ -0,0 +1,87 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"[PAD]": 84,
|
3 |
+
"[UNK]": 83,
|
4 |
+
"`": 1,
|
5 |
+
"|": 0,
|
6 |
+
"،": 2,
|
7 |
+
"ؑ": 3,
|
8 |
+
"ؓ": 4,
|
9 |
+
"ؔ": 5,
|
10 |
+
"؛": 6,
|
11 |
+
"؟": 7,
|
12 |
+
"ء": 8,
|
13 |
+
"آ": 9,
|
14 |
+
"أ": 10,
|
15 |
+
"ؤ": 11,
|
16 |
+
"ئ": 12,
|
17 |
+
"ا": 13,
|
18 |
+
"ب": 14,
|
19 |
+
"ت": 15,
|
20 |
+
"ث": 16,
|
21 |
+
"ج": 17,
|
22 |
+
"ح": 18,
|
23 |
+
"خ": 19,
|
24 |
+
"د": 20,
|
25 |
+
"ذ": 21,
|
26 |
+
"ر": 22,
|
27 |
+
"ز": 23,
|
28 |
+
"س": 24,
|
29 |
+
"ش": 25,
|
30 |
+
"ص": 26,
|
31 |
+
"ض": 27,
|
32 |
+
"ط": 28,
|
33 |
+
"ظ": 29,
|
34 |
+
"ع": 30,
|
35 |
+
"غ": 31,
|
36 |
+
"ف": 32,
|
37 |
+
"ق": 33,
|
38 |
+
"ك": 34,
|
39 |
+
"ل": 35,
|
40 |
+
"م": 36,
|
41 |
+
"ن": 37,
|
42 |
+
"ه": 38,
|
43 |
+
"و": 39,
|
44 |
+
"ى": 40,
|
45 |
+
"ي": 41,
|
46 |
+
"ً": 42,
|
47 |
+
"َ": 43,
|
48 |
+
"ُ": 44,
|
49 |
+
"ِ": 45,
|
50 |
+
"ّ": 46,
|
51 |
+
"ْ": 47,
|
52 |
+
"ٓ": 48,
|
53 |
+
"ٔ": 49,
|
54 |
+
"ٗ": 50,
|
55 |
+
"ٰ": 51,
|
56 |
+
"ٹ": 52,
|
57 |
+
"پ": 53,
|
58 |
+
"چ": 54,
|
59 |
+
"ڈ": 55,
|
60 |
+
"ڑ": 56,
|
61 |
+
"ژ": 57,
|
62 |
+
"ک": 58,
|
63 |
+
"گ": 59,
|
64 |
+
"ں": 60,
|
65 |
+
"ھ": 61,
|
66 |
+
"ہ": 62,
|
67 |
+
"ۂ": 63,
|
68 |
+
"ۃ": 64,
|
69 |
+
"ی": 65,
|
70 |
+
"ے": 66,
|
71 |
+
"ۓ": 67,
|
72 |
+
"۔": 68,
|
73 |
+
"’": 69,
|
74 |
+
"…": 70,
|
75 |
+
"ﭨ": 71,
|
76 |
+
"ﮭ": 72,
|
77 |
+
"ﮯ": 73,
|
78 |
+
"ﯾ": 74,
|
79 |
+
"ﷲ": 75,
|
80 |
+
"ﷺ": 76,
|
81 |
+
"ﺗ": 77,
|
82 |
+
"ﺘ": 78,
|
83 |
+
"ﺩ": 79,
|
84 |
+
"ﺲ": 80,
|
85 |
+
"ﻧ": 81,
|
86 |
+
"ﻮ": 82
|
87 |
+
}
|