Issue
์์คํ
์ฌ๋ถํ
ํด๋, ์ปจํ
์ด๋๋ฅผ ์ฌ๋ถํ
ํด๋ stt๋ก๊ทธ๊ฐ ๋น๋๋ค.
Detail
์๋์ ๊ฐ์ด, stt์ ๊ด๋ จ ์๋ ๊ณผ์ ์์ stt๋ก๊ทธ๊ฐ ๋น๋๋ค.
์์คํ
์์ฒด๋ฅผ ์ฌ๋ถํ
ํด๋ ๋ง์ฐฌ๊ฐ์ง์
๋๋ค.
์์์ผ๊น์ง ํด๊ฒฐ ์์ ์
๋๋ค. ๊ธฐ๋ค๋ ค์ฃผ์ธ์.
visual-radio | WARNING:tensorflow:From /usr/local/lib/python3.8/site-packages/spleeter/separator.py:146: calling DatasetV2.from_generator (from tensorflow.python.data.ops.dataset_ops) with output_types is deprecated and will be removed in a future version.
visual-radio | Instructions for updating:
visual-radio | Use output_signature instead
visual-radio | WARNING:tensorflow:From /usr/local/lib/python3.8/site-packages/spleeter/separator.py:146: calling DatasetV2.from_generator (from tensorflow.python.data.ops.dataset_ops) with output_shapes is deprecated and will be removed in a future version.
visual-radio | Instructions for updating:
visual-radio | Use output_signature instead
visual-radio | 2023-09-11 20:26:19 |DEBUG| services.py:273 ... services > [โโโโ] sec_wav_list: [['sec_0', array([0.19611222, 0.2103714 , 0.20772618, ..., 0.06323321, 0.05940634,
visual-radio | 0.05521922], dtype=float32)], ['sec_1', array([ 0.0512778 , 0.04856004, 0.04442124, ..., -0.10672967,
visual-radio | -0.11385804, -0.11091355], dtype=float32)], ['sec_2', array([-0.08002008, 0.00464832, -0.11666928, ..., -0.00225557,
visual-radio | -0.01346225, -0.01918887], dtype=float32)], ['sec_3', array([-0.01852008, -0.01298604, -0.00539833, ..., 0.09085913,
visual-radio | 0.06770968, 0.07900562], dtype=float32)], ['sec_4', array([ 0.07021023, 0.05995855, 0.05517017, ..., -0.1000219 ,
visual-radio | 0.00940602, 0.13087524], dtype=float32)]]
**
visual-radio | 2023-09-11 20:26:20 |DEBUG| stt.py:64 ... STT > [stt] start!
visual-radio | 2023-09-11 20:26:20 |DEBUG| stt.py:67 ... STT > [stt] ์ค๋์ค ๋ก๋์ค..
visual-radio | 2023-09-11 20:26:20 |DEBUG| stt.py:89 ... STT > [stt] DONE IN 0.382692813873291 SECONDS
visual-radio | 2023-09-11 20:26:20 |DEBUG| stt.py:150 ... STT > [stt] script ์์ฑ ์๋ฃ
visual-radio | 2023-09-11 20:26:20 |DEBUG| route.py:242 ... route > empty vocabulary; perhaps the documents only contain stop words
visual-radio | 2023-09-11 20:26:20 |DEBUG| route.py:243 ... route > ์ค๋ฅ ๋ฐ์!!!! ์ค๋์ค ์ฒ๋ฆฌ๋ฅผ ์ข
๋ฃํฉ๋๋ค.
visual-radio | 2023-09-11 20:26:20 |DEBUG| route.py:247 ... route > Traceback (most recent call last):
visual-radio | File "/app/VisualRadio/route.py", line 222, in process_audio_file
visual-radio | paragraph.compose_paragraph(broadcast, name, date) # stt๊ฐ ์ฌ์งํ๋๋ฉด ๋ฌธ๋จ๊ตฌ์ฑ๋ ์๋ก ํด์ผ ํจ
visual-radio | File "/app/./VisualRadio/paragraph.py", line 118, in compose_paragraph
visual-radio | vectorized = vectorizer.fit_transform(document)
visual-radio | File "/usr/local/lib/python3.8/site-packages/sklearn/feature_extraction/text.py", line 2126, in fit_transform
visual-radio | X = super().fit_transform(raw_documents)
visual-radio | File "/usr/local/lib/python3.8/site-packages/sklearn/base.py", line 1151, in wrapper
visual-radio | return fit_method(estimator, *args, **kwargs)
visual-radio | File "/usr/local/lib/python3.8/site-packages/sklearn/feature_extraction/text.py", line 1383, in fit_transform
visual-radio | vocabulary, X = self.count_vocab(raw_documents, self.fixed_vocabulary)
visual-radio | File "/usr/local/lib/python3.8/site-packages/sklearn/feature_extraction/text.py", line 1289, in _count_vocab
visual-radio | raise ValueError(
visual-radio | ValueError: empty vocabulary; perhaps the documents only contain stop words
visual-radio |
**
visual-radio | WARNING:tensorflow:From /usr/local/lib/python3.8/site-packages/keras/layers/normalization/batch_normalization.py:561: _colocate_with (from tensorflow.python.framework.ops) is deprecated and will be removed in a future version.
visual-radio | Instructions for updating:
visual-radio | Colocations handled automatically by placer.
Issue
์์คํ ์ฌ๋ถํ ํด๋, ์ปจํ ์ด๋๋ฅผ ์ฌ๋ถํ ํด๋ stt๋ก๊ทธ๊ฐ ๋น๋๋ค.
Detail
์๋์ ๊ฐ์ด, stt์ ๊ด๋ จ ์๋ ๊ณผ์ ์์ stt๋ก๊ทธ๊ฐ ๋น๋๋ค.
์์คํ ์์ฒด๋ฅผ ์ฌ๋ถํ ํด๋ ๋ง์ฐฌ๊ฐ์ง์ ๋๋ค.
์์์ผ๊น์ง ํด๊ฒฐ ์์ ์ ๋๋ค. ๊ธฐ๋ค๋ ค์ฃผ์ธ์.
visual-radio | WARNING:tensorflow:From /usr/local/lib/python3.8/site-packages/spleeter/separator.py:146: calling DatasetV2.from_generator (from tensorflow.python.data.ops.dataset_ops) with output_types is deprecated and will be removed in a future version.
visual-radio | Instructions for updating:
visual-radio | Use output_signature instead
visual-radio | WARNING:tensorflow:From /usr/local/lib/python3.8/site-packages/spleeter/separator.py:146: calling DatasetV2.from_generator (from tensorflow.python.data.ops.dataset_ops) with output_shapes is deprecated and will be removed in a future version.
visual-radio | Instructions for updating:
visual-radio | Use output_signature instead
visual-radio | 2023-09-11 20:26:19 |DEBUG| services.py:273 ... services > [โโโโ] sec_wav_list: [['sec_0', array([0.19611222, 0.2103714 , 0.20772618, ..., 0.06323321, 0.05940634,
visual-radio | 0.05521922], dtype=float32)], ['sec_1', array([ 0.0512778 , 0.04856004, 0.04442124, ..., -0.10672967,
visual-radio | -0.11385804, -0.11091355], dtype=float32)], ['sec_2', array([-0.08002008, 0.00464832, -0.11666928, ..., -0.00225557,
visual-radio | -0.01346225, -0.01918887], dtype=float32)], ['sec_3', array([-0.01852008, -0.01298604, -0.00539833, ..., 0.09085913,
visual-radio | 0.06770968, 0.07900562], dtype=float32)], ['sec_4', array([ 0.07021023, 0.05995855, 0.05517017, ..., -0.1000219 ,
visual-radio | 0.00940602, 0.13087524], dtype=float32)]]
**
visual-radio | 2023-09-11 20:26:20 |DEBUG| stt.py:64 ... STT > [stt] start!
visual-radio | 2023-09-11 20:26:20 |DEBUG| stt.py:67 ... STT > [stt] ์ค๋์ค ๋ก๋์ค..
visual-radio | 2023-09-11 20:26:20 |DEBUG| stt.py:89 ... STT > [stt] DONE IN 0.382692813873291 SECONDS
visual-radio | 2023-09-11 20:26:20 |DEBUG| stt.py:150 ... STT > [stt] script ์์ฑ ์๋ฃ
visual-radio | 2023-09-11 20:26:20 |DEBUG| route.py:242 ... route > empty vocabulary; perhaps the documents only contain stop words
visual-radio | 2023-09-11 20:26:20 |DEBUG| route.py:243 ... route > ์ค๋ฅ ๋ฐ์!!!! ์ค๋์ค ์ฒ๋ฆฌ๋ฅผ ์ข ๋ฃํฉ๋๋ค.
visual-radio | 2023-09-11 20:26:20 |DEBUG| route.py:247 ... route > Traceback (most recent call last):
visual-radio | File "/app/VisualRadio/route.py", line 222, in process_audio_file
visual-radio | paragraph.compose_paragraph(broadcast, name, date) # stt๊ฐ ์ฌ์งํ๋๋ฉด ๋ฌธ๋จ๊ตฌ์ฑ๋ ์๋ก ํด์ผ ํจ
visual-radio | File "/app/./VisualRadio/paragraph.py", line 118, in compose_paragraph
visual-radio | vectorized = vectorizer.fit_transform(document)
visual-radio | File "/usr/local/lib/python3.8/site-packages/sklearn/feature_extraction/text.py", line 2126, in fit_transform
visual-radio | X = super().fit_transform(raw_documents)
visual-radio | File "/usr/local/lib/python3.8/site-packages/sklearn/base.py", line 1151, in wrapper
visual-radio | return fit_method(estimator, *args, **kwargs)
visual-radio | File "/usr/local/lib/python3.8/site-packages/sklearn/feature_extraction/text.py", line 1383, in fit_transform
visual-radio | vocabulary, X = self.count_vocab(raw_documents, self.fixed_vocabulary)
visual-radio | File "/usr/local/lib/python3.8/site-packages/sklearn/feature_extraction/text.py", line 1289, in _count_vocab
visual-radio | raise ValueError(
visual-radio | ValueError: empty vocabulary; perhaps the documents only contain stop words
visual-radio |
**
visual-radio | WARNING:tensorflow:From /usr/local/lib/python3.8/site-packages/keras/layers/normalization/batch_normalization.py:561: _colocate_with (from tensorflow.python.framework.ops) is deprecated and will be removed in a future version.
visual-radio | Instructions for updating:
visual-radio | Colocations handled automatically by placer.