2022/12/05 - Amazon Transcribe Service - 3 updated api methods
Changes Amazon Transcribe now supports creating custom language models in the following languages: Japanese (ja-JP) and German (de-DE).
{'LanguageCode': {'de-DE', 'ja-JP'}}
Creates a new custom language model.
When creating a new custom language model, you must specify:
If you want a Wideband (audio sample rates over 16,000 Hz) or Narrowband (audio sample rates under 16,000 Hz) base model
The location of your training and tuning files (this must be an Amazon S3 URI)
The language of your model
A unique name for your model
See also: AWS API Documentation
Request Syntax
client.create_language_model(
LanguageCode='en-US'|'hi-IN'|'es-US'|'en-GB'|'en-AU'|'de-DE'|'ja-JP',
BaseModelName='NarrowBand'|'WideBand',
ModelName='string',
InputDataConfig={
'S3Uri': 'string',
'TuningDataS3Uri': 'string',
'DataAccessRoleArn': 'string'
},
Tags=[
{
'Key': 'string',
'Value': 'string'
},
]
)
string
[REQUIRED]
The language code that represents the language of your model. Each custom language model must contain terms in only one language, and the language you select for your custom language model must match the language of your training and tuning data.
For a list of supported languages and their associated language codes, refer to the Supported languages table. Note that US English ( en-US ) is the only language supported with Amazon Transcribe Medical.
A custom language model can only be used to transcribe files in the same language as the model. For example, if you create a custom language model using US English ( en-US ), you can only apply this model to files that contain English audio.
string
[REQUIRED]
The Amazon Transcribe standard language model, or base model, used to create your custom language model. Amazon Transcribe offers two options for base models: Wideband and Narrowband.
If the audio you want to transcribe has a sample rate of 16,000 Hz or greater, choose WideBand . To transcribe audio with a sample rate less than 16,000 Hz, choose NarrowBand .
string
[REQUIRED]
A unique name, chosen by you, for your custom language model.
This name is case sensitive, cannot contain spaces, and must be unique within an Amazon Web Services account. If you try to create a new custom language model with the same name as an existing custom language model, you get a ConflictException error.
dict
[REQUIRED]
Contains the Amazon S3 location of the training data you want to use to create a new custom language model, and permissions to access this location.
When using InputDataConfig , you must include these sub-parameters: S3Uri , which is the Amazon S3 location of your training data, and DataAccessRoleArn , which is the Amazon Resource Name (ARN) of the role that has permission to access your specified Amazon S3 location. You can optionally include TuningDataS3Uri , which is the Amazon S3 location of your tuning data. If you specify different Amazon S3 locations for training and tuning data, the ARN you use must have permissions to access both locations.
S3Uri (string) -- [REQUIRED]
The Amazon S3 location (URI) of the text files you want to use to train your custom language model.
Here's an example URI path: s3://DOC-EXAMPLE-BUCKET/my-model-training-data/
TuningDataS3Uri (string) --
The Amazon S3 location (URI) of the text files you want to use to tune your custom language model.
Here's an example URI path: s3://DOC-EXAMPLE-BUCKET/my-model-tuning-data/
DataAccessRoleArn (string) -- [REQUIRED]
The Amazon Resource Name (ARN) of an IAM role that has permissions to access the Amazon S3 bucket that contains your input files. If the role that you specify doesn’t have the appropriate permissions to access the specified Amazon S3 location, your request fails.
IAM role ARNs have the format arn:partition:iam::account:role/role-name-with-path . For example: arn:aws:iam::111122223333:role/Admin .
For more information, see IAM ARNs.
list
Adds one or more custom tags, each in the form of a key:value pair, to a new custom language model at the time you create this new model.
To learn more about using tags with Amazon Transcribe, refer to Tagging resources.
(dict) --
Adds metadata, in the form of a key:value pair, to the specified resource.
For example, you could add the tag Department:Sales to a resource to indicate that it pertains to your organization's sales department. You can also use tags for tag-based access control.
To learn more about tagging, see Tagging resources.
Key (string) -- [REQUIRED]
The first part of a key:value pair that forms a tag associated with a given resource. For example, in the tag Department:Sales , the key is 'Department'.
Value (string) -- [REQUIRED]
The second part of a key:value pair that forms a tag associated with a given resource. For example, in the tag Department:Sales , the value is 'Sales'.
Note that you can set the value of a tag to an empty string, but you can't set the value of a tag to null. Omitting the tag value is the same as using an empty string.
dict
Response Syntax
{
'LanguageCode': 'en-US'|'hi-IN'|'es-US'|'en-GB'|'en-AU'|'de-DE'|'ja-JP',
'BaseModelName': 'NarrowBand'|'WideBand',
'ModelName': 'string',
'InputDataConfig': {
'S3Uri': 'string',
'TuningDataS3Uri': 'string',
'DataAccessRoleArn': 'string'
},
'ModelStatus': 'IN_PROGRESS'|'FAILED'|'COMPLETED'
}
Response Structure
(dict) --
LanguageCode (string) --
The language code you selected for your custom language model.
BaseModelName (string) --
The Amazon Transcribe standard language model, or base model, you specified when creating your custom language model.
ModelName (string) --
The name of your custom language model.
InputDataConfig (dict) --
Lists your data access role ARN (Amazon Resource Name) and the Amazon S3 locations you provided for your training ( S3Uri ) and tuning ( TuningDataS3Uri ) data.
S3Uri (string) --
The Amazon S3 location (URI) of the text files you want to use to train your custom language model.
Here's an example URI path: s3://DOC-EXAMPLE-BUCKET/my-model-training-data/
TuningDataS3Uri (string) --
The Amazon S3 location (URI) of the text files you want to use to tune your custom language model.
Here's an example URI path: s3://DOC-EXAMPLE-BUCKET/my-model-tuning-data/
DataAccessRoleArn (string) --
The Amazon Resource Name (ARN) of an IAM role that has permissions to access the Amazon S3 bucket that contains your input files. If the role that you specify doesn’t have the appropriate permissions to access the specified Amazon S3 location, your request fails.
IAM role ARNs have the format arn:partition:iam::account:role/role-name-with-path . For example: arn:aws:iam::111122223333:role/Admin .
For more information, see IAM ARNs.
ModelStatus (string) --
The status of your custom language model. When the status displays as COMPLETED , your model is ready to use.
{'LanguageModel': {'LanguageCode': {'de-DE', 'ja-JP'}}}
Provides information about the specified custom language model.
This operation also shows if the base language model that you used to create your custom language model has been updated. If Amazon Transcribe has updated the base model, you can create a new custom language model using the updated base model.
If you tried to create a new custom language model and the request wasn't successful, you can use DescribeLanguageModel to help identify the reason for this failure.
See also: AWS API Documentation
Request Syntax
client.describe_language_model(
ModelName='string'
)
string
[REQUIRED]
The name of the custom language model you want information about. Model names are case sensitive.
dict
Response Syntax
{
'LanguageModel': {
'ModelName': 'string',
'CreateTime': datetime(2015, 1, 1),
'LastModifiedTime': datetime(2015, 1, 1),
'LanguageCode': 'en-US'|'hi-IN'|'es-US'|'en-GB'|'en-AU'|'de-DE'|'ja-JP',
'BaseModelName': 'NarrowBand'|'WideBand',
'ModelStatus': 'IN_PROGRESS'|'FAILED'|'COMPLETED',
'UpgradeAvailability': True|False,
'FailureReason': 'string',
'InputDataConfig': {
'S3Uri': 'string',
'TuningDataS3Uri': 'string',
'DataAccessRoleArn': 'string'
}
}
}
Response Structure
(dict) --
LanguageModel (dict) --
Provides information about the specified custom language model.
This parameter also shows if the base language model you used to create your custom language model has been updated. If Amazon Transcribe has updated the base model, you can create a new custom language model using the updated base model.
If you tried to create a new custom language model and the request wasn't successful, you can use this DescribeLanguageModel to help identify the reason for this failure.
ModelName (string) --
A unique name, chosen by you, for your custom language model.
This name is case sensitive, cannot contain spaces, and must be unique within an Amazon Web Services account.
CreateTime (datetime) --
The date and time the specified custom language model was created.
Timestamps are in the format YYYY-MM-DD'T'HH:MM:SS.SSSSSS-UTC . For example, 2022-05-04T12:32:58.761000-07:00 represents 12:32 PM UTC-7 on May 4, 2022.
LastModifiedTime (datetime) --
The date and time the specified custom language model was last modified.
Timestamps are in the format YYYY-MM-DD'T'HH:MM:SS.SSSSSS-UTC . For example, 2022-05-04T12:32:58.761000-07:00 represents 12:32 PM UTC-7 on May 4, 2022.
LanguageCode (string) --
The language code used to create your custom language model. Each custom language model must contain terms in only one language, and the language you select for your custom language model must match the language of your training and tuning data.
For a list of supported languages and their associated language codes, refer to the Supported languages table. Note that U.S. English ( en-US ) is the only language supported with Amazon Transcribe Medical.
BaseModelName (string) --
The Amazon Transcribe standard language model, or base model, used to create your custom language model.
ModelStatus (string) --
The status of the specified custom language model. When the status displays as COMPLETED the model is ready for use.
UpgradeAvailability (boolean) --
Shows if a more current base model is available for use with the specified custom language model.
If false , your custom language model is using the most up-to-date base model.
If true , there is a newer base model available than the one your language model is using.
Note that to update a base model, you must recreate the custom language model using the new base model. Base model upgrades for existing custom language models are not supported.
FailureReason (string) --
If ModelStatus is FAILED , FailureReason contains information about why the custom language model request failed. See also: Common Errors.
InputDataConfig (dict) --
The Amazon S3 location of the input files used to train and tune your custom language model, in addition to the data access role ARN (Amazon Resource Name) that has permissions to access these data.
S3Uri (string) --
The Amazon S3 location (URI) of the text files you want to use to train your custom language model.
Here's an example URI path: s3://DOC-EXAMPLE-BUCKET/my-model-training-data/
TuningDataS3Uri (string) --
The Amazon S3 location (URI) of the text files you want to use to tune your custom language model.
Here's an example URI path: s3://DOC-EXAMPLE-BUCKET/my-model-tuning-data/
DataAccessRoleArn (string) --
The Amazon Resource Name (ARN) of an IAM role that has permissions to access the Amazon S3 bucket that contains your input files. If the role that you specify doesn’t have the appropriate permissions to access the specified Amazon S3 location, your request fails.
IAM role ARNs have the format arn:partition:iam::account:role/role-name-with-path . For example: arn:aws:iam::111122223333:role/Admin .
For more information, see IAM ARNs.
{'Models': {'LanguageCode': {'de-DE', 'ja-JP'}}}
Provides a list of custom language models that match the specified criteria. If no criteria are specified, all custom language models are returned.
To get detailed information about a specific custom language model, use the operation.
See also: AWS API Documentation
Request Syntax
client.list_language_models(
StatusEquals='IN_PROGRESS'|'FAILED'|'COMPLETED',
NameContains='string',
NextToken='string',
MaxResults=123
)
string
Returns only custom language models with the specified status. Language models are ordered by creation date, with the newest model first. If you don't include StatusEquals , all custom language models are returned.
string
Returns only the custom language models that contain the specified string. The search is not case sensitive.
string
If your ListLanguageModels request returns more results than can be displayed, NextToken is displayed in the response with an associated string. To get the next page of results, copy this string and repeat your request, including NextToken with the value of the copied string. Repeat as needed to view all your results.
integer
The maximum number of custom language models to return in each page of results. If there are fewer results than the value that you specify, only the actual results are returned. If you don't specify a value, a default of 5 is used.
dict
Response Syntax
{
'NextToken': 'string',
'Models': [
{
'ModelName': 'string',
'CreateTime': datetime(2015, 1, 1),
'LastModifiedTime': datetime(2015, 1, 1),
'LanguageCode': 'en-US'|'hi-IN'|'es-US'|'en-GB'|'en-AU'|'de-DE'|'ja-JP',
'BaseModelName': 'NarrowBand'|'WideBand',
'ModelStatus': 'IN_PROGRESS'|'FAILED'|'COMPLETED',
'UpgradeAvailability': True|False,
'FailureReason': 'string',
'InputDataConfig': {
'S3Uri': 'string',
'TuningDataS3Uri': 'string',
'DataAccessRoleArn': 'string'
}
},
]
}
Response Structure
(dict) --
NextToken (string) --
If NextToken is present in your response, it indicates that not all results are displayed. To view the next set of results, copy the string associated with the NextToken parameter in your results output, then run your request again including NextToken with the value of the copied string. Repeat as needed to view all your results.
Models (list) --
Provides information about the custom language models that match the criteria specified in your request.
(dict) --
Provides information about a custom language model, including the base model name, when the model was created, the location of the files used to train the model, when the model was last modified, the name you chose for the model, its language, its processing state, and if there is an upgrade available for the base model.
ModelName (string) --
A unique name, chosen by you, for your custom language model.
This name is case sensitive, cannot contain spaces, and must be unique within an Amazon Web Services account.
CreateTime (datetime) --
The date and time the specified custom language model was created.
Timestamps are in the format YYYY-MM-DD'T'HH:MM:SS.SSSSSS-UTC . For example, 2022-05-04T12:32:58.761000-07:00 represents 12:32 PM UTC-7 on May 4, 2022.
LastModifiedTime (datetime) --
The date and time the specified custom language model was last modified.
Timestamps are in the format YYYY-MM-DD'T'HH:MM:SS.SSSSSS-UTC . For example, 2022-05-04T12:32:58.761000-07:00 represents 12:32 PM UTC-7 on May 4, 2022.
LanguageCode (string) --
The language code used to create your custom language model. Each custom language model must contain terms in only one language, and the language you select for your custom language model must match the language of your training and tuning data.
For a list of supported languages and their associated language codes, refer to the Supported languages table. Note that U.S. English ( en-US ) is the only language supported with Amazon Transcribe Medical.
BaseModelName (string) --
The Amazon Transcribe standard language model, or base model, used to create your custom language model.
ModelStatus (string) --
The status of the specified custom language model. When the status displays as COMPLETED the model is ready for use.
UpgradeAvailability (boolean) --
Shows if a more current base model is available for use with the specified custom language model.
If false , your custom language model is using the most up-to-date base model.
If true , there is a newer base model available than the one your language model is using.
Note that to update a base model, you must recreate the custom language model using the new base model. Base model upgrades for existing custom language models are not supported.
FailureReason (string) --
If ModelStatus is FAILED , FailureReason contains information about why the custom language model request failed. See also: Common Errors.
InputDataConfig (dict) --
The Amazon S3 location of the input files used to train and tune your custom language model, in addition to the data access role ARN (Amazon Resource Name) that has permissions to access these data.
S3Uri (string) --
The Amazon S3 location (URI) of the text files you want to use to train your custom language model.
Here's an example URI path: s3://DOC-EXAMPLE-BUCKET/my-model-training-data/
TuningDataS3Uri (string) --
The Amazon S3 location (URI) of the text files you want to use to tune your custom language model.
Here's an example URI path: s3://DOC-EXAMPLE-BUCKET/my-model-tuning-data/
DataAccessRoleArn (string) --
The Amazon Resource Name (ARN) of an IAM role that has permissions to access the Amazon S3 bucket that contains your input files. If the role that you specify doesn’t have the appropriate permissions to access the specified Amazon S3 location, your request fails.
IAM role ARNs have the format arn:partition:iam::account:role/role-name-with-path . For example: arn:aws:iam::111122223333:role/Admin .
For more information, see IAM ARNs.