Bump deepgram version #154
Merged
Conversation
This file contains 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
theomonnom
approved these changes
Feb 7, 2024
askable-nic
added a commit
to askableorg/aimod-poc-livekit-agent
that referenced
this pull request
Feb 8, 2024
commit 5fab872 Author: Neil Dwyer <[email protected]> Date: Tue Feb 6 17:18:48 2024 -0800 Kitt to handle empty deepgram text + elevenlabs bug fix (livekit#155) hotfix commit 7661824 Author: Neil Dwyer <[email protected]> Date: Tue Feb 6 16:25:35 2024 -0800 Bump deepgram version (livekit#154) commit ddc168e Author: Neil Dwyer <[email protected]> Date: Tue Feb 6 16:10:52 2024 -0800 Fixes to Elevenlabs (livekit#152) commit 5555526 Author: David Zhao <[email protected]> Date: Tue Feb 6 09:12:38 2024 -0800 Update KITT and other plugins to use end_of_speech field (livekit#153) * Update KITT and other plugins to use end_of_speech field Tested with KITT. It significantly improves the end of speech behavior so that we are giving it a 1s wait before starting to process user input. * ruff on 3.10 * use ruff action * fixed ruff commit a98a7c1 Author: Paul Lockett <[email protected]> Date: Tue Feb 6 00:02:51 2024 -0800 update tts init to export StreamAdapter (livekit#149) commit 604d7e3 Author: Sean Muirhead <[email protected]> Date: Mon Feb 5 21:35:55 2024 -0800 Update deepgram endpointing (livekit#145) * deepgram: Add min_silence_duration to deepgram client. deepgram controls vad by endpointing parameter, this fix allows to configure min_silence_duration in agents layer * add utterance_end_ms and speech_final to Deepgram plugin * add utterance_end_ms and speech_final to Deepgram plugin * expose speech_final as end_of_speech --------- Co-authored-by: Lam Nguyen <[email protected]>
askable-nic
added a commit
to askableorg/aimod-poc-livekit-agent
that referenced
this pull request
Feb 22, 2024
commit 5fab872 Author: Neil Dwyer <[email protected]> Date: Tue Feb 6 17:18:48 2024 -0800 Kitt to handle empty deepgram text + elevenlabs bug fix (livekit#155) hotfix commit 7661824 Author: Neil Dwyer <[email protected]> Date: Tue Feb 6 16:25:35 2024 -0800 Bump deepgram version (livekit#154) commit ddc168e Author: Neil Dwyer <[email protected]> Date: Tue Feb 6 16:10:52 2024 -0800 Fixes to Elevenlabs (livekit#152) commit 5555526 Author: David Zhao <[email protected]> Date: Tue Feb 6 09:12:38 2024 -0800 Update KITT and other plugins to use end_of_speech field (livekit#153) * Update KITT and other plugins to use end_of_speech field Tested with KITT. It significantly improves the end of speech behavior so that we are giving it a 1s wait before starting to process user input. * ruff on 3.10 * use ruff action * fixed ruff commit a98a7c1 Author: Paul Lockett <[email protected]> Date: Tue Feb 6 00:02:51 2024 -0800 update tts init to export StreamAdapter (livekit#149) commit 604d7e3 Author: Sean Muirhead <[email protected]> Date: Mon Feb 5 21:35:55 2024 -0800 Update deepgram endpointing (livekit#145) * deepgram: Add min_silence_duration to deepgram client. deepgram controls vad by endpointing parameter, this fix allows to configure min_silence_duration in agents layer * add utterance_end_ms and speech_final to Deepgram plugin * add utterance_end_ms and speech_final to Deepgram plugin * expose speech_final as end_of_speech --------- Co-authored-by: Lam Nguyen <[email protected]>
parshvadaftari
pushed a commit
to parshvadaftari/agents
that referenced
this pull request
Jun 23, 2024
* Begin tracing deepgram (and metrics) * More testing * Add FileInputDevice * Resolve mypy issues Remove unused imports and variables & fix type hints * Store tracers per instance in DeepgramTranscriber * Add opentelemetry metrics to AssemblyAITranscriber * Separate loading logic in FileInputDevice * Format DeepgramTranscriber * Add initial benchmarking script Benchmarking script currently works for Deepgram and AssemblyAI transcribers * Add argparse to benchmark script * Fix bug that logged every response as the first response * Add ChatGPT and Anthropic agent support, expand argparse options, and display correct outputs * Rename RespondAgent tracers with name of underlying model * Add JSON export * Begin synthesizer support * Add FileOutputDevice * Move spans inside async functions OpenTelemetry doesn't seem to have an async decorator * Update synthesizers to not use context in traces * Implement ElevenLabs synthesizer benchmark with FileOutputDevice * Add support for more synthesizers benchmark.py now supports ElevenLabs, Google, Azure, GTTS, and Bark * Only write to wave file on terminate * Save all results in separate folder * Add custom azure synthesizer tracing * Make terminate non-blocking by writing to file in separate thread * Support GPT4 and show logs * Ignore the default benchmark result location * Rename agent tracer * Catch synthesis exceptions * Add agent characters per second * Make agent naming consistent * Average over multiple runs * Set all num_cycles options at once if desired * Add graph generation * Fix mypy issues * Add option for transcription from microphone * Revert streaming_conversation.py * Add some docs about the benchmarking CLI app * Add note about matplotlib * Fix mypy issues * Support --trace in playground/synthesize.py * Move PrintDurationSpanExporter to new file * Support --trace in playground/transcribe.py * Small syntax tweaks * Support --trace in playground/agent/chat.py * Fix mypy issues * Really fix mypy issues * Add list of supported componenets to docs * Refactor argparser for chat and synthesize * Remove magic number * Fix types and duplicate variable name * Remove += string concatenation * Fix magic number for default silent duration * Move tracers to start of actual synthesis * Split synthesizer tracing into api response and conversion * Don't filter dict unnecessarily * Make constants all caps * Rename test audio file * Add create_graphs helper function * Refactor metric parsing logic * More descriptive variable naming * Reset streaming_conversation.py
SuJingnan
pushed a commit
to SuJingnan/agents
that referenced
this pull request
Nov 26, 2024
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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.
No description provided.