echogarden-project/echogarden issues and pull requests

#93 - Split long audio to chunks before sending it to cloud speech recognition services like OpenAI or Groq

Issue - State: open - Opened by MinmoTech 6 days ago - 1 comment
Labels: recognition, feature

#92 - Preserve Punctuation in Alignment Output

Issue - State: open - Opened by shanureddy4 12 days ago - 3 comments
Labels: feature

#91 - Synthesis.ts: fixed typo in symbol name

Pull Request - State: closed - Opened by Boorj 28 days ago

#90 - subtitles with timings

Issue - State: open - Opened by DiLfestr about 1 month ago - 2 comments
Labels: synthesis, feature

#89 - Options.md: Align, Whisper: added a note about `timestampAccuracy`

Pull Request - State: closed - Opened by kbulygin about 1 month ago

#88 - Development.md: fixed a typo in a link

Pull Request - State: closed - Opened by kbulygin about 1 month ago

#87 - Added VAD request capability to server

Pull Request - State: open - Opened by aabmets about 1 month ago - 1 comment

#86 - Added dependencies and updated project config

Pull Request - State: closed - Opened by aabmets about 2 months ago - 4 comments

#85 - ERROR: Invalid token: 51865

Issue - State: closed - Opened by smoores-dev about 2 months ago - 8 comments

#84 - Update command in CLI.md readme file

Pull Request - State: closed - Opened by ezekiel747 about 2 months ago - 1 comment

#83 - Re-voicing of video with translation

Issue - State: open - Opened by Alexandrsv 2 months ago - 1 comment

#82 - echogarden transcribe doesnt work

Issue - State: open - Opened by shrimp-alfredo 2 months ago - 1 comment

#81 - eSpeak-ng says "Chinese letter" or "Japanese letter" for Japanese characters it doesn't support, causing quality of `dtw` alignment and some synthesis engines to be degraded for Japanese

Issue - State: open - Opened by rotemdan 2 months ago
Labels: bug, synthesis, alignment, external

#80 - Amazon voice recognition fails

Issue - State: closed - Opened by Cyberax 2 months ago - 3 comments
Labels: bug, recognition

#79 - The best solution to avoid hallucinations on echogarden with whisper.cpp is?

Issue - State: closed - Opened by jc955 3 months ago - 4 comments

#78 - Align hangs in Windows 11

Issue - State: open - Opened by an-lee 3 months ago - 9 comments
Labels: more-info-needed

#77 - Could echogarden export `WhisperCppModelId` from the API?

Issue - State: closed - Opened by smoores-dev 3 months ago - 3 comments

#76 - Attempted import error: 'alawmulaw' does not contain a default export (imported as 'AlawMulaw')

Issue - State: closed - Opened by smoores-dev 3 months ago - 5 comments

#75 - fix: case issue in main field

Pull Request - State: closed - Opened by 0xFlicker 3 months ago - 10 comments

#74 - Recognize function: recognized words with embedded ellipses cause error with segment timeline

Issue - State: closed - Opened by dhouck 3 months ago - 10 comments

#73 - Wasm SIMD unsupported On AMD Ryzen

Issue - State: closed - Opened by smoores-dev 3 months ago - 6 comments

#72 - Optional ffmpeg

Issue - State: open - Opened by sevenlayercookie 4 months ago - 3 comments
Labels: enhancement

#71 - Importing library to google cloud functions syntax error

Issue - State: open - Opened by dwang3142 5 months ago - 2 comments
Labels: more-info-needed

#70 - align-transcript-and-translation error: Token '4' not found in text

Issue - State: open - Opened by IMBAepsilon 5 months ago - 1 comment
Labels: bug, alignment, more-info-needed

#69 - JS Heap out of Memory when Aligning (with isolate set to true)

Issue - State: closed - Opened by LordMartron94 5 months ago - 7 comments

#68 - Feature Request: Support Greek in Normal Alphabet (grc)

Issue - State: closed - Opened by LordMartron94 5 months ago

#67 - Error: "Couldn't find the word ... in the text"

Issue - State: closed - Opened by smoores-dev 6 months ago - 16 comments

#66 - Whisper ONNX model error during decoding: Non-zero status code returned while running Expand node

Issue - State: open - Opened by cvl01 7 months ago - 11 comments
Labels: bug, recognition, external

#65 - Whisper.cpp parseResultObject failure/edge case

Issue - State: closed - Opened by smoores-dev 7 months ago - 9 comments

#64 - eSpeak Out of Memory issue

Issue - State: closed - Opened by cvl01 7 months ago - 18 comments

#63 - Trouble running development environment

Issue - State: closed - Opened by cvl01 7 months ago - 2 comments

#62 - GPU acceleration + word level timestamps

Issue - State: closed - Opened by smoores-dev 7 months ago - 2 comments

#61 - Feature request: Only generate alignment of segments

Issue - State: closed - Opened by flo62134 7 months ago - 2 comments
Labels: feature

#60 - Feature Request: use `dtw-ra` with provided wordTimeline

Issue - State: open - Opened by an-lee 8 months ago - 11 comments
Labels: alignment, feature

#59 - Feature Request: Rate-independent audio search/match

Issue - State: open - Opened by smoores-dev 8 months ago - 7 comments
Labels: feature

#58 - a error threw when Extract timeline for part

Issue - State: closed - Opened by yhown589 8 months ago - 3 comments
Labels: bug

#57 - eSpeak-ng markers are not generated correctly for Korean language inputs, causing issues with synthesis and alignment of Korean

Issue - State: open - Opened by an-lee 9 months ago - 3 comments
Labels: bug, synthesis, alignment, external

#56 - "Error: No matching voice found" & "Error: No match found in uncrop timeline (should not occur)"

Issue - State: closed - Opened by an-lee 9 months ago - 2 comments

#55 - Using alignment for voiceover processing

Issue - State: open - Opened by gelsas 9 months ago - 1 comment
Labels: question, translation

#54 - Add operation to get a list of supported languages for recognition / alignment / translation engines

Issue - State: open - Opened by rotemdan 9 months ago
Labels: feature

#53 - Export supported languages for WhisperSTT

Pull Request - State: closed - Opened by rbozan 9 months ago - 3 comments

#52 - Fix crash on nodes <18.16.0 or 19.8.0

Pull Request - State: closed - Opened by FreedomBen 9 months ago - 7 comments

#51 - Error on Speech-to-transcript alignment for large audio files

Issue - State: closed - Opened by ezekiel747 10 months ago - 12 comments
Labels: bug

#50 - Python client logic for connecting the echogarden web socket

Issue - State: closed - Opened by iAmIlluminati 10 months ago - 1 comment
Labels: question

#49 - Small issue regarding error message ISO 639-2 codes and `Echogarden.recognize`

Issue - State: closed - Opened by rbozan 10 months ago - 2 comments
Labels: enhancement

#48 - espeak-ng.data cannot be found

Issue - State: closed - Opened by allen2peace 10 months ago - 16 comments
Labels: question

#47 - Error: Wave audio format id 3 is not supported

Issue - State: closed - Opened by Fatihcrim 11 months ago - 5 comments

#46 - Issues with Importing Echogarden

Issue - State: closed - Opened by ncioffi1 11 months ago - 6 comments
Labels: question

#45 - eSpeak doesn't work with the Polish language

Issue - State: closed - Opened by rbozan 11 months ago - 6 comments

#44 - Some issues when using echogarden in an Electron app

Issue - State: closed - Opened by an-lee 11 months ago - 12 comments

#43 - Overwriting a package instead of downloading it.

Issue - State: closed - Opened by rbozan 11 months ago - 15 comments

#42 - SMIL output format for the "alignment" command

Issue - State: open - Opened by Astorsoft 11 months ago - 8 comments
Labels: alignment, feature

#41 - is there an option to set it to run in the gpu?

Issue - State: closed - Opened by yhown589 12 months ago - 5 comments
Labels: question

#40 - justing thanks

Issue - State: closed - Opened by yhown589 12 months ago

#39 - a problem ocurred in text-to-speech

Issue - State: closed - Opened by yhown589 12 months ago - 2 comments

#38 - I have a question with the running

Issue - State: closed - Opened by yhown589 12 months ago - 5 comments

#37 - Aligment: is that a method to generate srt file in JS code?

Issue - State: closed - Opened by yhown589 12 months ago - 4 comments

#36 - Alignment: only dtw can generate .srt file, others engine cannot generate srt file

Issue - State: closed - Opened by yhown589 12 months ago - 4 comments

#35 - Problems aligning certain Japanese characters with Whisper engine

Issue - State: closed - Opened by fechan about 1 year ago - 3 comments
Labels: bug

#34 - Error with whisper large model

Issue - State: closed - Opened by raivisdejus about 1 year ago - 4 comments
Labels: bug, external

#33 - Different subtitle outputs with CLI commands

Issue - State: open - Opened by GalenMarek14 about 1 year ago - 1 comment
Labels: question, feature

#32 - All large whisper models missing from huggingface repo

Issue - State: open - Opened by halalsandwich about 1 year ago - 5 comments

#31 - Flite WASM Issues

Issue - State: closed - Opened by halalsandwich about 1 year ago - 1 comment

#30 - Modular imports causing error in API npm package

Issue - State: closed - Opened by hassannaftabb over 1 year ago - 12 comments
Labels: question

#29 - Investigate porting some of the engines to run in the browser

Issue - State: open - Opened by rotemdan over 1 year ago
Labels: feature, future

#28 - Develop web-based UI

Issue - State: open - Opened by rotemdan over 1 year ago - 3 comments
Labels: feature, future

#27 - Finish initial development of browser extension

Issue - State: open - Opened by rotemdan over 1 year ago
Labels: feature, future

#26 - Finish development of new text language detection engine

Issue - State: open - Opened by rotemdan over 1 year ago
Labels: feature, future

#25 - Alignment: automatically choose best window duration based on audio length, if not specified

Issue - State: closed - Opened by rotemdan over 1 year ago - 1 comment
Labels: enhancement, alignment

#24 - Error: Sentence has no word entries even though text can be found in audio

Issue - State: closed - Opened by flo62134 over 1 year ago - 8 comments

#24 - Error: Sentence has no word entries even though text can be found in audio

Issue - State: closed - Opened by flo62134 over 1 year ago - 7 comments

#24 - Error: Sentence has no word entries even though text can be found in audio

Issue - State: closed - Opened by flo62134 over 1 year ago - 7 comments

#23 - Alignment: DTW may give inaccurate results due to silent or non-speech sections

Issue - State: closed - Opened by Tendaliu over 1 year ago - 32 comments
Labels: bug, alignment

#22 - SoX playback unexpectedly stops after a few seconds on macOS

Issue - State: open - Opened by Tendaliu over 1 year ago - 23 comments
Labels: bug, cli

#22 - SoX playback unexpectedly stops after a few seconds on macOS

Issue - State: closed - Opened by Tendaliu over 1 year ago - 28 comments
Labels: bug, cli

#21 - Note: version `0.10.7` accidentally introduced an issue where a package installation may get corrupted (fixed on `0.10.9`)

Issue - State: closed - Opened by rotemdan over 1 year ago

#20 - Permission Denied Error when Trying to Create Directory in Root of D Drive

Issue - State: closed - Opened by Tendaliu over 1 year ago - 7 comments
Labels: bug, cli

#20 - Permission Denied Error when Trying to Create Directory in Root of D Drive

Issue - State: open - Opened by Tendaliu over 1 year ago - 6 comments
Labels: bug, cli

#20 - Permission Denied Error when Trying to Create Directory in Root of D Drive

Issue - State: open - Opened by Tendaliu over 1 year ago - 6 comments
Labels: bug, cli

#19 - Rules for splitting sentences on punctuation characters in subtitles

Issue - State: open - Opened by rotemdan over 1 year ago - 18 comments
Labels: question

#19 - Rules for splitting sentences on punctuation characters in subtitles

Issue - State: open - Opened by rotemdan over 1 year ago - 18 comments
Labels: question

#19 - Rules for splitting sentences on punctuation characters in subtitles

Issue - State: open - Opened by rotemdan over 1 year ago - 18 comments
Labels: question

#18 - What audio formats does the program support?

Issue - State: closed - Opened by rotemdan over 1 year ago - 8 comments
Labels: bug, question

#18 - What audio formats does the program support?

Issue - State: closed - Opened by rotemdan over 1 year ago - 8 comments
Labels: bug, question

#17 - package the Echogarden project into a standalone executable

Issue - State: open - Opened by Tendaliu over 1 year ago - 11 comments
Labels: question

#16 - Recognition: add support for OpenAI's cloud Whisper API

Issue - State: closed - Opened by rotemdan over 1 year ago - 1 comment
Labels: recognition, feature

#16 - Recognition: add support for OpenAI's cloud Whisper API

Issue - State: open - Opened by rotemdan over 1 year ago
Labels: recognition, feature

#15 - Synthesis: VITS voices have various pronunciation errors that can be fixed using lexicons

Issue - State: open - Opened by rotemdan over 1 year ago
Labels: bug, synthesis

#15 - Synthesis: VITS voices have various pronunciation errors that can be fixed using lexicons

Issue - State: open - Opened by rotemdan over 1 year ago
Labels: bug, synthesis

#14 - Synthesis: VITS voices have various issues related to model training

Issue - State: open - Opened by rotemdan over 1 year ago
Labels: bug, synthesis, external

#14 - Synthesis: VITS voices have various issues related to model training

Issue - State: open - Opened by rotemdan over 1 year ago
Labels: bug, synthesis, external