Deployed on AWS
Enhanced voice experience with accurate, real-time, scalable speech recognition
Overview
This solution uses state-of-the-art transformer-based models, performing speech processing for audio transcription. Designed with enterprise scalability in mind, it caters to the needs of businesses of all sizes. This solution ensures fast and accurate transcriptions, while optimizing resource utilization on CPU instances. This cost-effective approach empowers you to focus on what matters most – analyzing the wealth of information hidden within your audio recordings. This solution has the capability to handle multiple languages, facilitating seamless communication and understanding across diverse linguistic landscapes. It provides both batch and real-time inference capabilities. The batch mode enables efficient processing of extensive audio datasets, ensuring timely delivery of transcriptions for further analysis. Meanwhile, the real-time inference feature provides instantaneous transformation of spoken words into written text, enabling immediate access to vital information.
Highlights
- eNova Speech Recognition model is trained for speech recognition and transcription tasks, capable of transcribing speech audio into the text in the language it is spoken. This model version is tuned for CPU uses and best suitable for short audio segments. **Supported Langauge:** * 'en_us': 'English', * 'de_de': 'German', * 'es_419': 'Spanish', * 'ko_kr': 'Korean' **Supported Tasks:** * 'transcribe_srt': Transcription With srt. * 'transcribe': Transcription Task
- The solution can be used in industries like media and entertainment, software, mobile applications, hospitatlity, healthcare, legal etc. to provide transcription and closed captioning. This can also be used to develop many solutions requiring speech to text like voice bots and virtual assistants.
- Need more machine learning, deep learning, NLP and Quantum Computing solutions. Reach out to us at Harman DTS.
Details
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
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.m4.16xlarge Inference (Batch) Recommended | Model inference on the ml.m4.16xlarge instance type, batch mode | $40.00 |
ml.m5.2xlarge Inference (Real-Time) Recommended | Model inference on the ml.m5.2xlarge instance type, real-time mode | $10.00 |
ml.c5.18xlarge Inference (Batch) | Model inference on the ml.c5.18xlarge instance type, batch mode | $40.00 |
ml.c5.xlarge Inference (Batch) | Model inference on the ml.c5.xlarge instance type, batch mode | $40.00 |
ml.m4.2xlarge Inference (Batch) | Model inference on the ml.m4.2xlarge instance type, batch mode | $40.00 |
ml.m5.4xlarge Inference (Real-Time) | Model inference on the ml.m5.4xlarge instance type, real-time mode | $10.00 |
ml.m5.12xlarge Inference (Real-Time) | Model inference on the ml.m5.12xlarge instance type, real-time mode | $10.00 |
ml.g5.xlarge Inference (Real-Time) | Model inference on the ml.g5.xlarge instance type, real-time mode | $10.00 |
ml.c5.large Inference (Real-Time) | Model inference on the ml.c5.large instance type, real-time mode | $10.00 |
ml.m5.xlarge Inference (Real-Time) | Model inference on the ml.m5.xlarge instance type, real-time mode | $10.00 |
Vendor refund policy
We do not provide any usage related refunds at this time.
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
Bug fixes and enhancements
Additional details
Inputs
- Summary
Model input is a json request with the following payload
- 'wv_data' = base64 encoded audio
- 'task' = whether to perform a plain transcribed text "transcribe" or a subtitles file (srt format) "transcribe_srt"
- 'lang' = language of transcription ('en_us': 'English', 'de_de': 'German', 'es_419': 'Spanish', 'ko_kr': 'Korean')
- Limitations for input type
- * The input audio data should consist of complete audio files, rather than raw PCM data (wav, flac, RAW). * The input audio sample should be 16000 Hz or above. * The maximum audio file size for realtime inference is 20MB and for batch transform 50MB each file.
- Input MIME type
- audio/x-wav, application/json
https://github.com/HDTS-user/lifeware-speech-recognition/tree/main/sample_input
https://github.com/HDTS-user/lifeware-speech-recognition/tree/main/sample_input
Input data descriptions
The following table describes supported input data fields for real-time inference and batch transform.
Field name | Description | Constraints | Required |
|---|---|---|---|
'wv_data' | 'wv_data' = base64 encoded audio (wav, flac, RAW)
'task' = "transcribe" or "transcribe_srt"
'lang' = 'en_us': 'English', 'de_de': 'German', 'es_419': 'Spanish' or 'ko_kr': 'Korean' | Type: FreeText | Yes |
'task' | 'wv_data' = base64 encoded audio (wav, flac, RAW)
'task' = "transcribe" or "transcribe_srt"
'lang' = 'en_us': 'English', 'de_de': 'German', 'es_419': 'Spanish' or 'ko_kr': 'Korean' | Type: FreeText | Yes |
'lang' | 'wv_data' = base64 encoded audio (wav, flac, RAW)
'task' = "transcribe" or "transcribe_srt"
'lang' = 'en_us': 'English', 'de_de': 'German', 'es_419': 'Spanish' or 'ko_kr': 'Korean' | Type: FreeText | Yes |
Resources
Support
Vendor support
Business hours email support marketplaceSupp@harman.comÂ
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
Accurately convert your audio or video files into text or subtitles in seconds with embeddable Meetrix transcriber software. We support transcription in dozens of languages and dialects from around the world. Use advanced speech recognition with seamless integration through an easy-to-use API. The perfect low cost alternative for Amazon Transcribe.
The Heartbeat by IOanyT Innovations is a cutting-edge AI/ML-powered Call Analytics solution designed to produce exceptionally precise call transcripts and extract valuable conversation insights. Its primary objective is to enhance customer experience and boost agent productivity, providing businesses with actionable information for making informed decisions.
Transcribe and interpret spoken language across African languages with Lelapa AI's Vulavula Multilingual ASR Model.
Powered by advanced AI technologies, Fano Callinter is an intelligent omni-channel interaction analytics system designed to help enterprises to automatically transcribe calls, and then leverage AI to monitor interactions with customers to ensure compliance, improve customer experience and discover business insights.
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.