Sold by: KanjuTechÂ
Deployed on AWS
Free Trial
Brain-inspired models and cutting-edge transformers for transcription precision, unparalleled speaker identification, and labeling
Overview
KanjuTech's Transcription and Diarization model ensures secure end-to-end recognition of multi-participant conversations. It converts dialogue records into precise transcripts with labeled speakers and lines, offering automatic detection for any number of participants. With low error rates (WER and DER) for real-life data, it supports ten languages with human-level accuracy (WER 3-8%). The model efficiently handles over 12 hours of recording in just one hour on ml.p3.2xlarge. Following AWS's secure policy, only users can access processed data through SageMaker products. Industries like translation, transcription, media, broadcasting, call centers, corporate governance, and education will find our solution invaluable for enhancing their products and services.
Highlights
- Achieve human-level precision in transcription and diarization with our industry-grade solution. Seamlessly convert conversations into accurate transcriptions, complete with speaker detection and labeling. Your data is secure because only you have access as the user.
- Our model seamlessly accommodates widely used formats of pre-recorded audio and video inputs. Users can define the number of speakers or rely on automatic recognition for enhanced flexibility.
- Experience industry-grade transcription quality in 10 languages: English, Spanish, French, Portuguese, Russian, Indonesian, German, Japanese, Turkish, and Italian.
Details
Sold by
Categories
Delivery method
Latest version
Deployed on AWS
Unlock automation with AI agent solutions
Fast-track AI initiatives with agents, tools, and solutions from AWS Partners.
Features and programs
Financing for AWS Marketplace purchases
AWS Marketplace now accepts line of credit payments through the PNC Vendor Finance program. This program is available to select AWS customers in the US, excluding NV, NC, ND, TN, & VT.
Pricing
Free trial
Try this product free for 14 days according to the free trial terms set by the vendor.
Pricing is based on actual usage, with charges varying according to how much you consume. Subscriptions have no end date and may be canceled any time.
Additional AWS infrastructure costs may apply. Use the AWS Pricing Calculator to estimate your infrastructure costs.
Dimension | Description | Cost/host/hour |
|---|---|---|
ml.p3.2xlarge Inference (Batch) Recommended | Model inference on the ml.p3.2xlarge instance type, batch mode | $1.28 |
ml.p3.2xlarge Inference (Real-Time) Recommended | Model inference on the ml.p3.2xlarge instance type, real-time mode | $1.28 |
ml.p2.xlarge Inference (Batch) | Model inference on the ml.p2.xlarge instance type, batch mode | $0.38 |
ml.p2.xlarge Inference (Real-Time) | Model inference on the ml.p2.xlarge instance type, real-time mode | $0.38 |
ml.g4dn.4xlarge Inference (Real-Time) | Model inference on the ml.g4dn.4xlarge instance type, real-time mode | $0.51 |
ml.g4dn.16xlarge Inference (Real-Time) | Model inference on the ml.g4dn.16xlarge instance type, real-time mode | $1.82 |
ml.g5.xlarge Inference (Real-Time) | Model inference on the ml.g5.xlarge instance type, real-time mode | $0.47 |
ml.g5.8xlarge Inference (Real-Time) | Model inference on the ml.g5.8xlarge instance type, real-time mode | $1.02 |
ml.g4dn.2xlarge Inference (Real-Time) | Model inference on the ml.g4dn.2xlarge instance type, real-time mode | $0.32 |
ml.g5.4xlarge Inference (Real-Time) | Model inference on the ml.g5.4xlarge instance type, real-time mode | $0.68 |
Vendor refund policy
Please contact our support team: kanju@kanju.techÂ
Legal
Vendor terms and conditions
Upon subscribing to this product, you must acknowledge and agree to the terms and conditions outlined in the vendor's End User License Agreement (EULA)Â .
Content disclaimer
Vendors are responsible for their product descriptions and other product content. AWS does not warrant that vendors' product descriptions or other product content are accurate, complete, reliable, current, or error-free.
Delivery details
Amazon SageMaker model
An Amazon SageMaker model package is a pre-trained machine learning model ready to use without additional training. Use the model package to create a model on Amazon SageMaker for real-time inference or batch processing. Amazon SageMaker is a fully managed platform for building, training, and deploying machine learning models at scale.
Deploy the model on Amazon SageMaker AI using the following options:
Version release notes
Features improve
- Improved: A word level with timestamps was added to the output model. The data will allow you to get better-quality subtitles.
Additional details
Inputs
- Summary
The model supports common audio and video input formats. Due to AWS restrictions on the size of the input data, we recommend converting video files to audio before passing to the model.
- Limitations for input type
- The maximum audio file size for real-time inference is 15MB, and for batch transform jobs, it is 75MB for each file. The recommended duration of one audio file for real-time inference is limited to 11 minutes for ml.p3.2xlarge and 7 minutes for ml.g4dn.xlarge.
- Input MIME type
- application/json
https://github.com/KanjuTech/aws-marketplace/raw/main/example_input.wav
https://github.com/KanjuTech/aws-marketplace/raw/main/example_input.wav
Input data descriptions
The following table describes supported input data fields for real-time inference and batch transform.
Field name | Description | Constraints | Required |
|---|---|---|---|
'file' | Model input is a json request with the following payload:
'file' = base64 encoded audio
'language' = language of transcription ("auto" or a specific language, i.e. "en")
'num_speakers' = number of speakers ("auto" or a specific number, i.e. 2)
'f_name' = name of the input audio file | Type: FreeText | Yes |
'language' | Model input is a json request with the following payload:
'file' = base64 encoded audio
'language' = language of transcription ("auto" or a specific language, i.e. "en")
'num_speakers' = number of speakers ("auto" or a specific number, i.e. 2)
'f_name' = name of the input audio file | Type: FreeText | Yes |
'num_speakers' | Model input is a json request with the following payload:
'file' = base64 encoded audio
'language' = language of transcription ("auto" or a specific language, i.e. "en")
'num_speakers' = number of speakers ("auto" or a specific number, i.e. 2)
'f_name' = name of the input audio file | Type: FreeText | Yes |
'f_name' | Model input is a json request with the following payload:
'file' = base64 encoded audio
'language' = language of transcription ("auto" or a specific language, i.e. "en")
'num_speakers' = number of speakers ("auto" or a specific number, i.e. 2)
'f_name' = name of the input audio file | Type: FreeText | Yes |
Resources
Vendor resources
Support
Vendor support
If you have any questions about our product, please feel free to contact us. kanju@kanju.techÂ
AWS infrastructure support
AWS Support is a one-on-one, fast-response support channel that is staffed 24x7x365 with experienced and technical support engineers. The service helps customers of all sizes and technical abilities to successfully utilize the products and features provided by Amazon Web Services.
Similar products
Brain-inspired models and cutting-edge transformers for data-safe real-time language detection
Customer reviews
No customer reviews yet
Be the first to review this product . We've partnered with PeerSpot to gather customer feedback. You can share your experience by writing or recording a review, or scheduling a call with a PeerSpot analyst.