feat: Add comprehensive STT usage metrics tracking #2843
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Implement detailed usage metrics for Speech-to-Text (STT) services across all providers. This enables monitoring of performance, quality, and cost metrics for transcription operations. Changes: - Add STTUsage and STTUsageMetricsData classes to core metrics module - Implement metrics collection in base STTService class - Add metrics support to all STT service providers: * AssemblyAI, AWS, Azure, Cartesia * Deepgram (standard and Flux) * ElevenLabs, Fal, Gladia, Google * Riva, Soniox, Speechmatics, Whisper - Extend FrameProcessor with metrics reporting capabilities - Update RTVI framework to support STT metrics - Add frame processor metrics module for centralized metric handling Metrics tracked: - Content: word count, character count - Performance: processing time, real-time factor (RTF), words per second, time to first transcript (TTFT), time to final transcript - Quality: average confidence, word error rate (WER), proper noun accuracy - Audio metadata: sample rate, channels, encoding - Cost: cost per word, estimated total cost This implementation provides comprehensive observability for STT operations, enabling performance optimization and cost tracking across all supported providers.
|
This PR is in response to issue #1933 |
|
@markbackman may you look into this PR? |
|
@markbackman Hi, do you have a sense when this will be released? Many thanks! |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Implement detailed usage metrics for Speech-to-Text (STT) services across all providers. This enables monitoring of performance, quality, and cost metrics for transcription operations.
Changes:
Metrics tracked:
This implementation provides comprehensive observability for STT operations, enabling performance optimization and cost tracking across all supported providers.