I am trying to do a task of "Speech2Text" using transformer model in Hugging Face.
I tried the code in this documentation on hugging face
import torch
from transformers import Speech2TextProcessor, Speech2TextForConditionalGeneration
from datasets import load_dataset
model = Speech2TextForConditionalGeneration.from_pretrained("facebook/s2t-small-librispeech-asr")
processor = Speech2TextProcessor.from_pretrained("facebook/s2t-small-librispeech-asr")
ds = load_dataset("hf-internal-testing/librispeech_asr_demo", "clean", split="validation")
inputs = processor(ds[0]["audio"]["array"], sampling_rate=ds[0]["audio"]["sampling_rate"], return_tensors="pt")
generated_ids = model.generate(inputs["input_features"], attention_mask=inputs["attention_mask"])
transcription = processor.batch_decode(generated_ids)
transcription
but when I tried to run this code in Google Colab I am receiving the following error :
SystemError: google/protobuf/pyext/descriptor.cc:358: bad argument to internal function
On checking the other error lines it seems that on calling processor(), return_tesnors is None even though it is specified as pt. Due to which code is importing tensorflow and that error is coming. (know issue)
Full error message :
SystemError Traceback (most recent call last)
<ipython-input-4-2a3231ef630c> in <module>
9 ds = load_dataset("hf-internal-testing/librispeech_asr_demo", "clean", split="validation")
10
---> 11 inputs = processor(ds[0]["audio"]["array"], sampling_rate=ds[0]["audio"]["sampling_rate"], return_tensors="pt")
12
13 generated_ids = model.generate(inputs["input_features"], attention_mask=inputs["attention_mask"])
10 frames
/usr/local/lib/python3.7/dist-packages/transformers/models/speech_to_text/processing_speech_to_text.py in __call__(self, *args, **kwargs)
51 information.
52 """
---> 53 return self.current_processor(*args, **kwargs)
54
55 def batch_decode(self, *args, **kwargs):
/usr/local/lib/python3.7/dist-packages/transformers/models/speech_to_text/feature_extraction_speech_to_text.py in __call__(self, raw_speech, padding, max_length, truncation, pad_to_multiple_of, return_tensors, sampling_rate, return_attention_mask, **kwargs)
230 pad_to_multiple_of=pad_to_multiple_of,
231 return_attention_mask=return_attention_mask,
--> 232 **kwargs,
233 )
234
/usr/local/lib/python3.7/dist-packages/transformers/feature_extraction_sequence_utils.py in pad(self, processed_features, padding, max_length, truncation, pad_to_multiple_of, return_attention_mask, return_tensors)
161
162 if return_tensors is None:
--> 163 if is_tf_available() and _is_tensorflow(first_element):
164 return_tensors = "tf"
165 elif is_torch_available() and _is_torch(first_element):
/usr/local/lib/python3.7/dist-packages/transformers/utils/generic.py in _is_tensorflow(x)
96
97 def _is_tensorflow(x):
---> 98 import tensorflow as tf
99
100 return isinstance(x, tf.Tensor)
/usr/local/lib/python3.7/dist-packages/tensorflow/__init__.py in <module>
35 import typing as _typing
36
---> 37 from tensorflow.python.tools import module_util as _module_util
38 from tensorflow.python.util.lazy_loader import LazyLoader as _LazyLoader
39
/usr/local/lib/python3.7/dist-packages/tensorflow/python/__init__.py in <module>
35
36 from tensorflow.python import pywrap_tensorflow as _pywrap_tensorflow
---> 37 from tensorflow.python.eager import context
38
39 # pylint: enable=wildcard-import
/usr/local/lib/python3.7/dist-packages/tensorflow/python/eager/context.py in <module>
27 import six
28
---> 29 from tensorflow.core.framework import function_pb2
30 from tensorflow.core.protobuf import config_pb2
31 from tensorflow.core.protobuf import coordination_config_pb2
/usr/local/lib/python3.7/dist-packages/tensorflow/core/framework/function_pb2.py in <module>
14
15
---> 16 from tensorflow.core.framework import attr_value_pb2 as tensorflow_dot_core_dot_framework_dot_attr__value__pb2
17 from tensorflow.core.framework import node_def_pb2 as tensorflow_dot_core_dot_framework_dot_node__def__pb2
18 from tensorflow.core.framework import op_def_pb2 as tensorflow_dot_core_dot_framework_dot_op__def__pb2
/usr/local/lib/python3.7/dist-packages/tensorflow/core/framework/attr_value_pb2.py in <module>
14
15
---> 16 from tensorflow.core.framework import tensor_pb2 as tensorflow_dot_core_dot_framework_dot_tensor__pb2
17 from tensorflow.core.framework import tensor_shape_pb2 as tensorflow_dot_core_dot_framework_dot_tensor__shape__pb2
18 from tensorflow.core.framework import types_pb2 as tensorflow_dot_core_dot_framework_dot_types__pb2
/usr/local/lib/python3.7/dist-packages/tensorflow/core/framework/tensor_pb2.py in <module>
14
15
---> 16 from tensorflow.core.framework import resource_handle_pb2 as tensorflow_dot_core_dot_framework_dot_resource__handle__pb2
17 from tensorflow.core.framework import tensor_shape_pb2 as tensorflow_dot_core_dot_framework_dot_tensor__shape__pb2
18 from tensorflow.core.framework import types_pb2 as tensorflow_dot_core_dot_framework_dot_types__pb2
/usr/local/lib/python3.7/dist-packages/tensorflow/core/framework/resource_handle_pb2.py in <module>
148 ,
149 'DESCRIPTOR' : _RESOURCEHANDLEPROTO,
--> 150 '__module__' : 'tensorflow.core.framework.resource_handle_pb2'
151 # @@protoc_insertion_point(class_scope:tensorflow.ResourceHandleProto)
152 })
SystemError: google/protobuf/pyext/descriptor.cc:358: bad argument to internal function
here's my colab link for reference
Let me know what can be done to resolve this error
Thank you