rustygentile / real-time-voice-cloning Goto Github PK

Perhaps it is a permissions issue with AWS or perhaps I am missing something but I believe that create_model.py is supposed to deploy an initial model to S3 so that I can train it. When I run the install script, which calls create_model.py, and then try to run the example jupyter notebook I get the following errors on the transform block that starts the job:

`ClientError Traceback (most recent call last)
~/anaconda3/envs/amazonei_tensorflow2_p36/lib/python3.6/site-packages/sagemaker/transformer.py in _retrieve_image_name(self)
238 model_desc = self.sagemaker_session.sagemaker_client.describe_model(
--> 239 ModelName=self.model_name
240 )

~/anaconda3/envs/amazonei_tensorflow2_p36/lib/python3.6/site-packages/botocore/client.py in _api_call(self, *args, **kwargs)
315 # The "self" in this scope is referring to the BaseClient.
--> 316 return self._make_api_call(operation_name, kwargs)
317

~/anaconda3/envs/amazonei_tensorflow2_p36/lib/python3.6/site-packages/botocore/client.py in _make_api_call(self, operation_name, api_params)
634 error_class = self.exceptions.from_code(error_code)
--> 635 raise error_class(parsed_response, operation_name)
636 else:

ClientError: An error occurred (ValidationException) when calling the DescribeModel operation: Could not find model "arn:aws:sagemaker:us-east-1:525578525493:model/voice-cloning-recall".

During handling of the above exception, another exception occurred:

ValueError Traceback (most recent call last)
in
1 # Start the job. It should take several minutes. Although most of that is from starting the container.
----> 2 trans.transform(f's3://{bucket_name}/sample_job.json', content_type='application/json')
3 trans.wait()

~/anaconda3/envs/amazonei_tensorflow2_p36/lib/python3.6/site-packages/sagemaker/transformer.py in transform(self, data, data_type, content_type, compression_type, split_type, job_name, input_filter, output_filter, join_source, experiment_config, model_client_config, wait, logs)
193
194 if base_name is None:
--> 195 base_name = self._retrieve_base_name()
196
197 self._current_job_name = name_from_base(base_name)

~/anaconda3/envs/amazonei_tensorflow2_p36/lib/python3.6/site-packages/sagemaker/transformer.py in _retrieve_base_name(self)
226 def _retrieve_base_name(self):
227 """Placeholder docstring"""
--> 228 image_name = self._retrieve_image_name()
229
230 if image_name:

~/anaconda3/envs/amazonei_tensorflow2_p36/lib/python3.6/site-packages/sagemaker/transformer.py in _retrieve_image_name(self)
254 "Failed to fetch model information for %s. "
255 "Please ensure that the model exists. "
--> 256 "Local instance types require locally created models." % self.model_name
257 )
258

ValueError: Failed to fetch model information for voice-cloning-recall. Please ensure that the model exists. Local instance types require locally created models.`

Looking at the S3 bucket I don't see a model named "voice-cloning-recall" so I am pretty sure this is the issue. The create_model.py appears to be where the issue is?