Will you upload the ARK-ASR-3B (Transformers native) version?

#3
by Toko97 - opened

There is an issue with the trust_remote_code=True path!The expected correct outcome was to transcribe and generate Japanese subtitles, but the final result was garbled text! It involved at least 15 different languages!It's exactly the same issue I ran into while using another ASR model!https://huggingface.co/CohereLabs/cohere-transcribe-03-2026/discussions/28

Loading ARK-ASR-3B model from C:\Users\supervip.cache\huggingface\hub\models--AutoArk-AI--ARK-ASR-3B\snapshots\1e28271b79edc97635783bea65abc89195a09ed3...
Loading weights: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 926/926 [00:00<00:00, 3131.44it/s]

1
00:00:15,500 --> 00:00:16,199
ไธ‰ไธ‡ๅ—็š„

2
00:00:49,000 --> 00:00:50,899
ใ‚ใฎๆ™‚ใฎใŠ็คผใŒ่จ€ใ„ใŸใ„ใ ใ‘

3
00:01:12,700 --> 00:01:17,074
ano fujima
san nara kou

4
00:01:17,074 --> 00:01:18,299
chou
desu kedo ah

5
00:01:18,900 --> 00:01:21,000
ใŠ็–ฒใ‚Œๆง˜ใง
ใ™ ็ทๅ‹™ใฎ็ถพๅทใงใ™

6
00:01:21,799 --> 00:01:23,400
ๆ–ฐใ—ใ„ๅๆ‰€ใ‚’็งใซๆฅใŸใ‚“ใง

7
00:01:25,500 --> 00:01:26,900
ใ‚ใ‹ใ‚Šใพใ—ใ‚‡ใ†ใ‹.

8
00:01:27,099 --> 00:01:28,472
็›ดๆŽฅๆธกใ™ใฎใŒๆฑบใพใ‚Šใชใฎใงใง

9
00:01:28,472 --> 00:01:29,844
ใ‚‚็š†ใ•ใ‚“็ฝฎใ„ใฆใใพใ™ใ‚ˆใ‚ใ‚“

10
00:01:29,844 --> 00:01:32,799
ใฉใใ•ใ„ใงใ—ใ‚‡ใ†ๅคงไธˆๅคซใงใ™

11
00:01:33,000 --> 00:01:34,099
ใพใŸๆ˜Žๆ—ฅใใพใ™

12
00:01:34,599 --> 00:01:36,700
ใ”่ฆชๅˆ‡ใซใ‚
ใ‚ŠใŒใจใ†ใ”ใ–ใ„ใพใ™

13
00:01:51,200 --> 00:01:52,000
sasajima
shi ni

14
00:02:06,400 --> 00:02:12,000
sumimasen.
ๆ–ฐใ—ใ„ๅๅˆบใ‚’ๆธกใ—ใซๆฅใพใ—ใŸ

15
00:02:12,199 --> 00:02:14,599
ใ“ใกใ‚‰ใซๅ—ใ‘ๅ–
ใ‚Šใฎใ‚ตใ‚คใƒณใ‚’ใŠ้ก˜ใ„ใ—ใพใ™

16
00:02:15,199 --> 00:02:17,099
ใƒใ‚นใ‚ซใƒซใ‚ญใƒฉใ—ใฆใŸใ‹ใ‚‰

17
00:02:17,300 --> 00:02:22,400
thank you
very much. ๆ˜ฏ็š„

18
00:02:24,000 --> 00:02:24,500
hi.

19
00:02:53,699 --> 00:02:54,845
was a new
employee, a

20
00:02:54,845 --> 00:03:00,000
kawa aiko. so

21
00:03:04,699 --> 00:03:05,900
็งใฎๆฉไบบใงใ™

22
00:03:06,300 --> 00:03:08,900
ใจไฟบใ‚’ใ„ใŸใ‹
ใฃใŸใ‚“ใงใ™ ๆดชๆ€ป๏ผŒไฝ 

23
00:03:09,599 --> 00:03:11,800
ใ„ใ‚„ใ„ใ‚„ไฟบใฏๅˆฅใซ

24
00:03:12,599 --> 00:03:17,400
ๆˆ‘ไปฌ้ƒฝๅœจๅ•Š you c
an. yeah.

25
00:03:47,500 --> 00:03:50,500
ใ—่ฆ‹ใคใ‘ใก
ใ‚ƒใฃใŸ nanyo

26
00:03:51,599 --> 00:03:55,900
ใ“ใฎๅ‰่ฉฑใ—ใŸใงใ—
ใ‚‡ๆญฃไธ€ใฎ็ตๅฉš็›ธๆ‰‹ Oh.

27
00:03:56,400 --> 00:03:57,400
hong kong

28
00:03:59,699 --> 00:04:03,900
three
more i see

29
00:04:04,599 --> 00:04:07,900
็‰นใ•ใ‚Œใชใ‚“ใ‹ๅˆ†ใ‹ใ‚Œใฆใใ‚Œใ
ใ†ใชใ“ใ†่ฆ‹ใคใ‘ใŸใ‹ใ‚‰

30
00:04:11,599 --> 00:04:18,000
ใ“ใฎ ็”ทๆ€ง็ตŒ้จ“ใŒใชใ•ใใ†ใง
ใพใ˜ใ‚ใง็ฐกๅ˜ใซ่ฝใกใใ†

31
00:04:20,000 --> 00:04:26,500
็งใฎๆกไปถใ‚’ๅฎŒ็’งใซ
ใ‚ฏใƒชใ‚ขใ—ใฆใ‚‹ใ‚“ใ ใ‚ˆใญ ้ƒฝ

32
00:04:33,199 --> 00:04:34,100
jimi suki

33
00:04:35,899 --> 00:04:38,000
ไป–ใซใ‚‚้…ๅถ่€…ใฏใ„ใ‚‹ใ‚“ใ ใ‘ใฉ

34
00:04:38,300 --> 00:04:39,500
้€่ฟ‡ไป–็š„็”Ÿๆ—ฅ

35
00:04:43,500 --> 00:04:44,935
ใƒˆใ‚ฆใ‚ญใƒŽใ‚ฏใฎ่ฉฑใซใ‚ˆใ‚‹ใจๅฎถๆ—

36
00:04:44,935 --> 00:04:46,370
ใฎไผš่ฉฑใจใ‹ใง้ฃฒใฟไผšใซใฏใปใจ

37
00:04:46,370 --> 00:04:48,800
ใ‚“ใฉๅ‚ๅŠ ใ—ใชใ„ใฟใŸใ„

38
00:04:59,100 --> 00:05:01,100
ใงใ‚‚้“ๅ ดใชใ‚“ใฆใ—ใชใ„ใงใ‚ˆใญ

39
00:05:02,399 --> 00:05:04,500
ใ“ใ‚ŒใฏใŸใ ใฎ
ใ‚ซใƒ ใƒ•ใƒฉใƒผใ‚ธใƒฅใชใ‚“ใ ใ‚

40
00:05:08,800 --> 00:05:09,300
what do you

41
00:05:19,399 --> 00:05:21,199
ๆœฌๆฐ—ใงๅฅฝใใซใชใ‚‹ใ‚ใ‘ใชใ„ใ‹

42
00:05:23,800 --> 00:05:27,100
itadakimasu.
I got some.

43
00:05:28,199 --> 00:05:29,399
ใŠ็–ฒใ‚Œๆง˜ใงใ™

44
00:05:33,000 --> 00:05:34,800
yeah

45
00:05:35,000 --> 00:05:37,600
ๅคงใ—ใŸใ‚‚ใฎใ˜ใ‚ƒใชใ„ใงใ™ ใ‚ต
ใƒœใ‚‹ใจใใ‚‚ใ‚ใ‚Šใพใ™ใ—

46
00:05:42,500 --> 00:05:46,000
yeah.
as you saw

47
00:05:48,899 --> 00:05:51,100
ๆ˜ผ้ฃฏไธ€็ท’ใซใฉใ†ใ‹ใช

48
00:05:51,399 --> 00:05:54,800
ไป•ไบ‹ใฎ่ฉฑใ‚‚ใ‚†
ใฃใใ‚Šใ—ใŸใ„ใ— ่ฎฉๆฑŸ

49
00:05:55,500 --> 00:05:56,399
what is it

50
00:05:58,600 --> 00:05:59,600
ใ‚€ใ‚€ใ‚Šใ—ใชใ„ใ 

51
00:06:00,399 --> 00:06:01,995
้ƒจ็ฝฒใŒ้•ใฃใฆใ‚‚ใญไธ€ๅฟœไธŠๅธใจ

52
00:06:01,995 --> 00:06:03,590
้ƒจไธ‹ใ ใ—ใƒใƒฉใ‚นใƒกใƒณใƒˆใฟใŸใ„

53
00:06:03,590 --> 00:06:05,800
ใซใชใฃใฆใ‚‚ๅ›ฐใ‚‹ใ—

54
00:06:08,800 --> 00:06:14,199
thank you.
i don't know

55
00:06:15,000 --> 00:06:15,500
or the

Audio8 org

Hi, we are working on the transformers integration PR ;). Please stay tuned.

Sign up or log in to comment