How to train and evaluate on Hindi accent (speech to text).
- There is an audio file in Hindi mixed with English (few words that are used common) now i need translate Hindi audio to English as text.
- find the sentiment on the transcribed words
@bharath.vadithya I’m not sure I understand your post here, are you asking for how to do the three items ? Are you exploring alternatives to support Hindi ? Please elaborate.
Hi @lissyx… I have edited the question… i need those two items to complete. yes i am exploring alternatives to support Hindi, so that i an train my model better to understand Hindi and can transcribe to English. Thanks
Do you want to analyze emotions ? This is out of the scope of what we do
I’m unsure here, you want to transcribe Hindi, with a few common words of English ?
yeah i want to transcribe Hindi, with few common words of English.
alright, I understand this !!
Then you would need a training dataset in Hindi, I guess. And you could add the (expected?) english words in your language model?
yeah now i got the training data… where i can add it … (I am new to this area)
Can you read the documentation ? This should be covered quite correctly.
where it is ?? the gihub one !!
what about windows ??? actually i don’t have linux or mac
It may work but we don’t use that. It looks like TensorFlow GPU is supported there. That’s the best I can tell.
is there any ds_ctcdecoder for windows platform… the wheel file which is present in the github command line is linux supported.
No, we don’t have that (yet?).
but the above link says that if i can prefer … i can build the wheel file from source… here is the guide link iam following below
I am unsure what you are referring to here. We don’t support building the decoder for Windows, period.
hi @lissyx … i am trying to train my own model training. i got some problem and unable to figure out.
i guess some path error, but still i got this
- ‘[’ ‘!’ -f DeepSpeech.py ‘]’
- python3 -u DeepSpeech.py --train_files minigir/miniger-train.csv --dev_files minigir/miniger-train.csv --test_files minigir/miniger-train.csv --train_batch_size 48 --dev_batch_size 40 --test_batch_size 40 --n_hidden 1024 --epochs 64 --early_stop True --es_steps 6 --es_mean_th 0.1 --es_std_th 0.1 --dropout_rate 0.30 s
Traceback (most recent call last):
File “/home/metlife-vad/.local/lib/python3.7/site-packages/pandas/core/indexes/base.py”, line 4736, in get_value
return libindex.get_value_box(s, key)
File “pandas/_libs/index.pyx”, line 51, in pandas._libs.index.get_value_box
File “pandas/_libs/index.pyx”, line 47, in pandas._libs.index.get_value_at
File “pandas/_libs/util.pxd”, line 98, in pandas._libs.util.get_value_at
File “pandas/_libs/util.pxd”, line 83, in pandas._libs.util.validate_indexer
TypeError: ‘str’ object cannot be interpreted as an integer
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File “/home/metlife-vad/DeepSpeech/util/text.py”, line 85, in text_to_char_array
transcript = np.asarray(alphabet.encode(series[‘transcript’]))
File “/home/metlife-vad/.local/lib/python3.7/site-packages/pandas/core/series.py”, line 1071, in getitem
result = self.index.get_value(self, key)
File “/home/metlife-vad/.local/lib/python3.7/site-packages/pandas/core/indexes/base.py”, line 4744, in get_value
raise e1
File “/home/metlife-vad/.local/lib/python3.7/site-packages/pandas/core/indexes/base.py”, line 4730, in get_value
return self._engine.get_value(s, k, tz=getattr(series.dtype, “tz”, None))
File “pandas/_libs/index.pyx”, line 80, in pandas._libs.index.IndexEngine.get_value
File “pandas/_libs/index.pyx”, line 88, in pandas._libs.index.IndexEngine.get_value
File “pandas/_libs/index.pyx”, line 131, in pandas._libs.index.IndexEngine.get_loc
File “pandas/_libs/hashtable_class_helper.pxi”, line 1607, in pandas._libs.hashtable.PyObjectHashTable.get_item
File “pandas/_libs/hashtable_class_helper.pxi”, line 1614, in pandas._libs.hashtable.PyObjectHashTable.get_item
KeyError: ‘transcript’
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File “DeepSpeech.py”, line 931, in
absl.app.run(main)
File “/home/metlife-vad/.local/lib/python3.7/site-packages/absl/app.py”, line 299, in run
_run_main(main, args)
File “/home/metlife-vad/.local/lib/python3.7/site-packages/absl/app.py”, line 250, in _run_main
sys.exit(main(argv))
File “DeepSpeech.py”, line 915, in main
train()
File “DeepSpeech.py”, line 435, in train
train_phase=True)
File “/home/metlife-vad/DeepSpeech/util/feeding.py”, line 101, in create_dataset
df[‘transcript’] = df.apply(text_to_char_array, alphabet=Config.alphabet, result_type=‘reduce’, axis=1)
File “/home/metlife-vad/.local/lib/python3.7/site-packages/pandas/core/frame.py”, line 6928, in apply
return op.get_result()
File “/home/metlife-vad/.local/lib/python3.7/site-packages/pandas/core/apply.py”, line 186, in get_result
return self.apply_standard()
File “/home/metlife-vad/.local/lib/python3.7/site-packages/pandas/core/apply.py”, line 292, in apply_standard
self.apply_series_generator()
File “/home/metlife-vad/.local/lib/python3.7/site-packages/pandas/core/apply.py”, line 321, in apply_series_generator
results[i] = self.f(v)
File “/home/metlife-vad/.local/lib/python3.7/site-packages/pandas/core/apply.py”, line 112, in f
return func(x, *args, **kwds)
File “/home/metlife-vad/DeepSpeech/util/text.py”, line 91, in text_to_char_array
raise ValueError(‘While processing: {}\n{}’.format(series[‘wav_filename’], e))
ValueError: (“While processing: /home/metlife-vad/DeepSpeech/minigir/wav/tmp.wav\n’transcript’”, ‘occurred at index 0’)