Hugging Face's logo

Spaces:
jhj0517
/
Whisper-WebUI
Running

App Files Community
1
Whisper-WebUI
File size: 16,661 Bytes 
2699a55
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
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
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
 
en: # English
  Language: Language
  File: File
  Youtube: Youtube
  Mic: Mic
  T2T Translation: T2T Translation
  BGM Separation: BGM Separation
  GENERATE SUBTITLE FILE: GENERATE SUBTITLE FILE
  Output: Output
  Downloadable output file: Downloadable output file
  Upload File here: Upload File here
  Model: Model
  Automatic Detection: Automatic Detection
  File Format: File Format
  Translate to English?: Translate to English?
  Add a timestamp to the end of the filename: Add a timestamp to the end of the filename
  Advanced Parameters: Advanced Parameters
  Background Music Remover Filter: Background Music Remover Filter
  Enabling this will remove background music: Enabling this will remove background music by submodel before transcribing
  Enable Background Music Remover Filter: Enable Background Music Remover Filter
  Save separated files to output: Save separated files to output
  Offload sub model after removing background music: Offload sub model after removing background music
  Voice Detection Filter: Voice Detection Filter
  Enable this to transcribe only detected voice: Enable this to transcribe only detected voice parts by submodel.
  Enable Silero VAD Filter: Enable Silero VAD Filter
  Diarization: Diarization
  Enable Diarization: Enable Diarization
  HuggingFace Token: HuggingFace Token
  This is only needed the first time you download the model: This is only needed the first time you download the model. If you already have models, you don't need to enter. To download the model, you must manually go to "https://huggingface.co/pyannote/speaker-diarization-3.1" and "https://huggingface.co/pyannote/segmentation-3.0" and agree to their requirement.
  Device: Device
  Youtube Link: Youtube Link
  Youtube Thumbnail: Youtube Thumbnail
  Youtube Title: Youtube Title
  Youtube Description: Youtube Description
  Record with Mic: Record with Mic
  Upload Subtitle Files to translate here: Upload Subtitle Files to translate here
  Your Auth Key (API KEY): Your Auth Key (API KEY)
  Source Language: Source Language
  Target Language: Target Language
  TRANSLATE SUBTITLE FILE: TRANSLATE SUBTITLE FILE
  Upload Audio Files to separate background music: Upload Audio Files to separate background music
  Instrumental: Instrumental
  Vocals: Vocals
  SEPARATE BACKGROUND MUSIC: SEPARATE BACKGROUND MUSIC

ko: # Korean
  Language: μ–Έμ–΄
  File: 파일
  Youtube: 유튜브
  Mic: 마이크
  T2T Translation: T2T μžλ§‰ λ²ˆμ—­
  BGM Separation: λ°°κ²½ μŒμ•… 뢄리
  GENERATE SUBTITLE FILE: μžλ§‰ 파일 생성
  Output: κ²°κ³Όλ¬Ό
  Downloadable output file: κ²°κ³Όλ¬Ό 파일 λ‹€μš΄λ‘œλ“œ
  Upload File here: νŒŒμΌμ„ μ—…λ‘œλ“œ ν•˜μ„Έμš”
  Model: λͺ¨λΈ
  Automatic Detection: μžλ™ 감지
  File Format: 파일 ν˜•μ‹
  Translate to English?: μ˜μ–΄λ‘œ λ²ˆμ—­ν•©λ‹ˆκΉŒ? (μœ„μŠ€νΌ λͺ¨λΈ 자체 λ²ˆμ—­ κΈ°λŠ₯)
  Add a timestamp to the end of the filename: 파일 이름 끝에 νƒ€μž„μŠ€νƒœν”„ λ”ν•˜κΈ°
  Advanced Parameters: κ³ κΈ‰ λ³€μˆ˜
  Background Music Remover Filter: λ°°κ²½ μŒμ•… 제거 ν•„ν„°
  Enabling this will remove background music: λ°›μ•„μ“°κΈ° 이전에 λ¨Όμ € λ°°κ²½ μŒμ•…μ„ μ œκ±°ν•  μ„œλΈŒ λͺ¨λΈμ„ ν™œμ„±ν™” ν•©λ‹ˆλ‹€.
  Enable Background Music Remover Filter: λ°°κ²½ μŒμ•… 제거 ν•„ν„°λ₯Ό ν™œμ„±ν™” ν•©λ‹ˆλ‹€.
  Save separated files to output: λΆ„λ¦¬ν•œ 파일 λ”°λ‘œ 좜λ ₯ 폴더에 μ €μž₯
  Offload sub model after removing background music: λ°°κ²½ μŒμ•… 제거 ν›„ μ„œλΈŒλͺ¨λΈμ„ λΉ„ν™œμ„±ν™” ν•©λ‹ˆλ‹€. (VRAM 이 λΆ€μ‘±ν•  μ‹œ μ²΄ν¬ν•˜μ„Έμš”.)
  Voice Detection Filter: λͺ©μ†Œλ¦¬ 감지 ν•„ν„°
  Enable this to transcribe only detected voice: μ„œλΈŒ λͺ¨λΈμ— μ˜ν•΄ κ°μ§€λœ λͺ©μ†Œλ¦¬ λΆ€λΆ„λ§Œ λ°›μ•„μ“°κΈ°λ₯Ό μ§„ν–‰ν•©λ‹ˆλ‹€.
  Enable Silero VAD Filter: Silero VAD ν•„ν„° ν™œμ„±ν™” 
  Diarization: ν™”μž ꡬ뢄
  Enable Diarization: ν™”μž ꡬ뢄 ν™œμ„±ν™” 
  HuggingFace Token: ν—ˆκΉ…νŽ˜μ΄μŠ€ 토큰
  This is only needed the first time you download the model: 졜초둜 λͺ¨λΈμ„ λ‹€μš΄λ°›μ„ λ•Œλ§Œ 토큰이 ν•„μš”ν•©λ‹ˆλ‹€. 이미 λ‹€μš΄λ‘œλ“œ λ°›μœΌμ‹  μƒνƒœλΌλ©΄ μž…λ ₯ν•˜μ§€ μ•Šμ•„λ„ λ©λ‹ˆλ‹€. λͺ¨λΈμ„ λ‹€μš΄ λ°›κΈ° μœ„ν•΄μ„  "https://huggingface.co/pyannote/speaker-diarization-3.1" 와 "https://huggingface.co/pyannote/segmentation-3.0" μ—μ„œ λ¨Όμ € μ‚¬μš© 지침에 λ™μ˜ν•˜μ…”μ•Ό ν•©λ‹ˆλ‹€.
  Device: μ‚¬μš© κΈ°κΈ°
  Youtube Link: 유튜브 링크
  Youtube Thumbnail: 유튜브 썸넀일
  Youtube Title: 유튜브 제λͺ©
  Youtube Description: 유튜브 μ„€λͺ…
  Record with Mic: 마이크둜 λ…ΉμŒν•˜μ„Έμš”
  Upload Subtitle Files to translate here: λ²ˆμ—­ν•  μžλ§‰ νŒŒμΌμ„ μ—…λ‘œλ“œ ν•˜μ„Έμš”
  Your Auth Key (API KEY): DeepL API ν‚€
  Source Language: 원본 μ–Έμ–΄
  Target Language: λŒ€μƒ μ–Έμ–΄
  TRANSLATE SUBTITLE FILE: μžλ§‰ 파일 λ²ˆμ—­
  Upload Audio Files to separate background music: λ°°κ²½ μŒμ•…μ„ 뢄리할 μ˜€λ””μ˜€ νŒŒμΌμ„ μ—…λ‘œλ“œ ν•˜μ„Έμš”
  Instrumental: μ•…κΈ°
  Vocals: 보컬
  SEPARATE BACKGROUND MUSIC: λ°°κ²½ μŒμ•… 뢄리

ja: # Japanese
  Language: 言θͺž
  File: File
  Youtube: Youtube
  Mic: Mic
  T2T Translation: T2T Translation
  BGM Separation: BGM Separation
  GENERATE SUBTITLE FILE: GENERATE SUBTITLE FILE
  Output: Output
  Downloadable output file: Downloadable output file
  Upload File here: Upload File here
  Model: Model
  Automatic Detection: Automatic Detection
  File Format: File Format
  Translate to English?: Translate to English?
  Add a timestamp to the end of the filename: Add a timestamp to the end of the filename
  Advanced Parameters: Advanced Parameters
  Background Music Remover Filter: Background Music Remover Filter
  Enabling this will remove background music: Enabling this will remove background music by submodel before transcribing
  Enable Background Music Remover Filter: Enable Background Music Remover Filter
  Save separated files to output: Save separated files to output
  Offload sub model after removing background music: Offload sub model after removing background music
  Voice Detection Filter: Voice Detection Filter
  Enable this to transcribe only detected voice: Enable this to transcribe only detected voice parts by submodel.
  Enable Silero VAD Filter: Enable Silero VAD Filter
  Diarization: Diarization
  Enable Diarization: Enable Diarization
  HuggingFace Token: HuggingFace Token
  This is only needed the first time you download the model: This is only needed the first time you download the model. If you already have models, you don't need to enter. To download the model, you must manually go to "https://huggingface.co/pyannote/speaker-diarization-3.1" and "https://huggingface.co/pyannote/segmentation-3.0" and agree to their requirement.
  Device: Device
  Youtube Link: Youtube Link
  Youtube Thumbnail: Youtube Thumbnail
  Youtube Title: Youtube Title
  Youtube Description: Youtube Description
  Record with Mic: Record with Mic
  Upload Subtitle Files to translate here: Upload Subtitle Files to translate here
  Your Auth Key (API KEY): Your Auth Key (API KEY)
  Source Language: Source Language
  Target Language: Target Language
  TRANSLATE SUBTITLE FILE: TRANSLATE SUBTITLE FILE
  Upload Audio Files to separate background music: Upload Audio Files to separate background music
  Instrumental: Instrumental
  Vocals: Vocals
  SEPARATE BACKGROUND MUSIC: SEPARATE BACKGROUND MUSIC

es: # Spanish
  Language: Idioma
  File: File
  Youtube: Youtube
  Mic: Mic
  T2T Translation: T2T Translation
  BGM Separation: BGM Separation
  GENERATE SUBTITLE FILE: GENERATE SUBTITLE FILE
  Output: Output
  Downloadable output file: Downloadable output file
  Upload File here: Upload File here
  Model: Model
  Automatic Detection: Automatic Detection
  File Format: File Format
  Translate to English?: Translate to English?
  Add a timestamp to the end of the filename: Add a timestamp to the end of the filename
  Advanced Parameters: Advanced Parameters
  Background Music Remover Filter: Background Music Remover Filter
  Enabling this will remove background music: Enabling this will remove background music by submodel before transcribing
  Enable Background Music Remover Filter: Enable Background Music Remover Filter
  Save separated files to output: Save separated files to output
  Offload sub model after removing background music: Offload sub model after removing background music
  Voice Detection Filter: Voice Detection Filter
  Enable this to transcribe only detected voice: Enable this to transcribe only detected voice parts by submodel.
  Enable Silero VAD Filter: Enable Silero VAD Filter
  Diarization: Diarization
  Enable Diarization: Enable Diarization
  HuggingFace Token: HuggingFace Token
  This is only needed the first time you download the model: This is only needed the first time you download the model. If you already have models, you don't need to enter. To download the model, you must manually go to "https://huggingface.co/pyannote/speaker-diarization-3.1" and "https://huggingface.co/pyannote/segmentation-3.0" and agree to their requirement.
  Device: Device
  Youtube Link: Youtube Link
  Youtube Thumbnail: Youtube Thumbnail
  Youtube Title: Youtube Title
  Youtube Description: Youtube Description
  Record with Mic: Record with Mic
  Upload Subtitle Files to translate here: Upload Subtitle Files to translate here
  Your Auth Key (API KEY): Your Auth Key (API KEY)
  Source Language: Source Language
  Target Language: Target Language
  TRANSLATE SUBTITLE FILE: TRANSLATE SUBTITLE FILE
  Upload Audio Files to separate background music: Upload Audio Files to separate background music
  Instrumental: Instrumental
  Vocals: Vocals
  SEPARATE BACKGROUND MUSIC: SEPARATE BACKGROUND MUSIC

fr: # French
  Language: Langue
  File: File
  Youtube: Youtube
  Mic: Mic
  T2T Translation: T2T Translation
  BGM Separation: BGM Separation
  GENERATE SUBTITLE FILE: GENERATE SUBTITLE FILE
  Output: Output
  Downloadable output file: Downloadable output file
  Upload File here: Upload File here
  Model: Model
  Automatic Detection: Automatic Detection
  File Format: File Format
  Translate to English?: Translate to English?
  Add a timestamp to the end of the filename: Add a timestamp to the end of the filename
  Advanced Parameters: Advanced Parameters
  Background Music Remover Filter: Background Music Remover Filter
  Enabling this will remove background music: Enabling this will remove background music by submodel before transcribing
  Enable Background Music Remover Filter: Enable Background Music Remover Filter
  Save separated files to output: Save separated files to output
  Offload sub model after removing background music: Offload sub model after removing background music
  Voice Detection Filter: Voice Detection Filter
  Enable this to transcribe only detected voice: Enable this to transcribe only detected voice parts by submodel.
  Enable Silero VAD Filter: Enable Silero VAD Filter
  Diarization: Diarization
  Enable Diarization: Enable Diarization
  HuggingFace Token: HuggingFace Token
  This is only needed the first time you download the model: This is only needed the first time you download the model. If you already have models, you don't need to enter. To download the model, you must manually go to "https://huggingface.co/pyannote/speaker-diarization-3.1" and "https://huggingface.co/pyannote/segmentation-3.0" and agree to their requirement.
  Device: Device
  Youtube Link: Youtube Link
  Youtube Thumbnail: Youtube Thumbnail
  Youtube Title: Youtube Title
  Youtube Description: Youtube Description
  Record with Mic: Record with Mic
  Upload Subtitle Files to translate here: Upload Subtitle Files to translate here
  Your Auth Key (API KEY): Your Auth Key (API KEY)
  Source Language: Source Language
  Target Language: Target Language
  TRANSLATE SUBTITLE FILE: TRANSLATE SUBTITLE FILE
  Upload Audio Files to separate background music: Upload Audio Files to separate background music
  Instrumental: Instrumental
  Vocals: Vocals
  SEPARATE BACKGROUND MUSIC: SEPARATE BACKGROUND MUSIC

de: # German
  Language: Sprache
  File: File
  Youtube: Youtube
  Mic: Mic
  T2T Translation: T2T Translation
  BGM Separation: BGM Separation
  GENERATE SUBTITLE FILE: GENERATE SUBTITLE FILE
  Output: Output
  Downloadable output file: Downloadable output file
  Upload File here: Upload File here
  Model: Model
  Automatic Detection: Automatic Detection
  File Format: File Format
  Translate to English?: Translate to English?
  Add a timestamp to the end of the filename: Add a timestamp to the end of the filename
  Advanced Parameters: Advanced Parameters
  Background Music Remover Filter: Background Music Remover Filter
  Enabling this will remove background music: Enabling this will remove background music by submodel before transcribing
  Enable Background Music Remover Filter: Enable Background Music Remover Filter
  Save separated files to output: Save separated files to output
  Offload sub model after removing background music: Offload sub model after removing background music
  Voice Detection Filter: Voice Detection Filter
  Enable this to transcribe only detected voice: Enable this to transcribe only detected voice parts by submodel.
  Enable Silero VAD Filter: Enable Silero VAD Filter
  Diarization: Diarization
  Enable Diarization: Enable Diarization
  HuggingFace Token: HuggingFace Token
  This is only needed the first time you download the model: This is only needed the first time you download the model. If you already have models, you don't need to enter. To download the model, you must manually go to "https://huggingface.co/pyannote/speaker-diarization-3.1" and "https://huggingface.co/pyannote/segmentation-3.0" and agree to their requirement.
  Device: Device
  Youtube Link: Youtube Link
  Youtube Thumbnail: Youtube Thumbnail
  Youtube Title: Youtube Title
  Youtube Description: Youtube Description
  Record with Mic: Record with Mic
  Upload Subtitle Files to translate here: Upload Subtitle Files to translate here
  Your Auth Key (API KEY): Your Auth Key (API KEY)
  Source Language: Source Language
  Target Language: Target Language
  TRANSLATE SUBTITLE FILE: TRANSLATE SUBTITLE FILE
  Upload Audio Files to separate background music: Upload Audio Files to separate background music
  Instrumental: Instrumental
  Vocals: Vocals
  SEPARATE BACKGROUND MUSIC: SEPARATE BACKGROUND MUSIC

zh: # Chinese
  Language: 语言
  File: File
  Youtube: Youtube
  Mic: Mic
  T2T Translation: T2T Translation
  BGM Separation: BGM Separation
  GENERATE SUBTITLE FILE: GENERATE SUBTITLE FILE
  Output: Output
  Downloadable output file: Downloadable output file
  Upload File here: Upload File here
  Model: Model
  Automatic Detection: Automatic Detection
  File Format: File Format
  Translate to English?: Translate to English?
  Add a timestamp to the end of the filename: Add a timestamp to the end of the filename
  Advanced Parameters: Advanced Parameters
  Background Music Remover Filter: Background Music Remover Filter
  Enabling this will remove background music: Enabling this will remove background music by submodel before transcribing
  Enable Background Music Remover Filter: Enable Background Music Remover Filter
  Save separated files to output: Save separated files to output
  Offload sub model after removing background music: Offload sub model after removing background music
  Voice Detection Filter: Voice Detection Filter
  Enable this to transcribe only detected voice: Enable this to transcribe only detected voice parts by submodel.
  Enable Silero VAD Filter: Enable Silero VAD Filter
  Diarization: Diarization
  Enable Diarization: Enable Diarization
  HuggingFace Token: HuggingFace Token
  This is only needed the first time you download the model: This is only needed the first time you download the model. If you already have models, you don't need to enter. To download the model, you must manually go to "https://huggingface.co/pyannote/speaker-diarization-3.1" and "https://huggingface.co/pyannote/segmentation-3.0" and agree to their requirement.
  Device: Device
  Youtube Link: Youtube Link
  Youtube Thumbnail: Youtube Thumbnail
  Youtube Title: Youtube Title
  Youtube Description: Youtube Description
  Record with Mic: Record with Mic
  Upload Subtitle Files to translate here: Upload Subtitle Files to translate here
  Your Auth Key (API KEY): Your Auth Key (API KEY)
  Source Language: Source Language
  Target Language: Target Language
  TRANSLATE SUBTITLE FILE: TRANSLATE SUBTITLE FILE
  Upload Audio Files to separate background music: Upload Audio Files to separate background music
  Instrumental: Instrumental
  Vocals: Vocals
  SEPARATE BACKGROUND MUSIC: SEPARATE BACKGROUND MUSIC