Skip to content

Commit

Permalink
Update README.md
Browse files Browse the repository at this point in the history
  • Loading branch information
I5UCC committed Feb 20, 2023
1 parent 60839ec commit 49af12b
Showing 1 changed file with 22 additions and 9 deletions.
31 changes: 22 additions & 9 deletions README.md
Original file line number Diff line number Diff line change
Expand Up @@ -83,7 +83,17 @@ If you have problems with this program, try this to fix it:

You can either Edit this configuration manually by editing the ***config.json*** file, or you can change those settings in the Program itself by clicking "Settings" in the bottom right: <br>
You can hover over any of the options to get a brief explanation on what that option does.
![image](https://user-images.githubusercontent.com/43730681/214884754-4a4263d6-0ab3-4db3-b886-10c824145ea3.png)
![image](https://user-images.githubusercontent.com/43730681/220126409-be4eabb9-2a93-4fc7-b747-aff5188c065d.png)

You can edit Word replacements by clicking the "Edit Word Replacements" button:

![image](https://user-images.githubusercontent.com/43730681/220126862-c398ffe6-8114-43de-ac76-6854f5e32217.png)

You can edit the emote settings by clicking the "Edit Emotes" button:

![image](https://user-images.githubusercontent.com/43730681/220127049-225f20b7-6153-4e93-8dc1-734f4414a935.png)

## config.json

| Option | Values | Default | Explanation |
|:------:|:------:|:-------:|:-----------:|
Expand All @@ -93,18 +103,21 @@ You can hover over any of the options to get a brief explanation on what that op
| "model" | "tiny", "base", "small", "medium", "large" | base | What model of whisper to use. I'd recommend not going over "base" as it will significantly impact the performance |
| "language" | "english", "german", "spanish", "" | english | Language to use, "english" will be faster then other languages. Leaving it empty "", will let the program decide what language you are speaking. |
| "hotkey" | Any key supported by the [python keyboard library](https://github.com/boppreh/keyboard) | F1 | The key that is used to trigger listening. |
| "mode" | 0, 1, 2 | 0 | Transcribe mode to use 0 = once, 1 = once_continuous, 2 = realtime
| "dynamic_energy_threshold" | true, false | false | With dynamic_energy_threshold set to 'True', the program will continuously try to re-adjust the energy threshold to match the environment based on the ambient noise level at that time. I'd recommend setting the 'energy_threshold' value high when enabling this setting. |
| "energy_threshold" | 0-3500 | 200 | Under 'ideal' conditions (such as in a quiet room), values between 0 and 100 are considered silent or ambient, and values 300 to about 3500 are considered speech. |
| "pause_threshold" | 0.0-10.0 | 0.8 | Amount of seconds to wait when current energy is under the 'energy_threshold' |
| "timeout_time" | 0.0-10.0 | 3.0 | Amount of time to wait for the user to speak before timeout |
| "hold_time" | 0.0-10.0 | 1.5 | amount of time to hold the button to clear the Textbox |
| "max_transcribe_time" | 0.0-20.0 | 0.0 | maximum amount of time for transcribing a message before transcribing gets cancelled. 0.0 is infinite |
| "pause_threshold" | 0.0- | 0.8 | Amount of seconds to wait when current energy is under the 'energy_threshold' |
| "timeout_time" | 0.0- | 3.0 | Amount of time to wait for the user to speak before timeout |
| "hold_time" | 0.0- | 1.5 | amount of time to hold the button to clear the Textbox |
| "phrase_time_limit" | 0.0- | 2.0 | The maximum number of seconds that this will allow a phrase to continue before stopping and returning the part of the phrase processed before the time limit was reached |
| "max_transcribe_time" | 0.0- | 0.0 | maximum amount of time for transcribing a message before transcribing gets cancelled. 0.0 is infinite |
| "microphone_index" | null, 0-10 | null | Index of the microphone to use. null is the System Default mircophone. |
| "banned_words" | ["word1", "word2", ...] | null | Array of banned words that are gonna get removed from the transcribed text. |
| "word_replacements" | {"word1": "replacement1", "word2": "replacement2"} | {} | Array of banned words that are gonna get removed from the transcribed text. |
| "use_textbox" | true, false | true | If you want to send your text to VRChats Textbox. |
| "use_kat" | true, false | true | If you want to send your text to [KillFrenzyAvatarText](https://github.com/killfrenzy96/KillFrenzyAvatarText). |
| "use_both" | true, false | false | If you want to send your text to both options above, if both available and set to true. If not, the program will prefer sending to [KillFrenzyAvatarText](https://github.com/killfrenzy96/KillFrenzyAvatarText) if it is available. |
| "use_cpu" | true, false | false | Use CPU to transcribe, Always on if you downloaded the CPU version of this program. |
| "use_cpu" | true, false | false | Use CPU to transcribe, Always on if you downloaded the CPU version of this program. (Not editable on runtime) |
| "emotes" | - | - | All up to 80 emote slots and their corresponding phrase.

There are five model sizes, four with English-only versions, offering speed and accuracy tradeoffs. Below are the names of the available models and their approximate memory requirements and relative speed.

Expand Down Expand Up @@ -135,8 +148,8 @@ If it doesnt show up, manually register the ´app.vrmanifest´ file by double cl
- ~~Add a quick entry box for quick messaging.~~
- ~~Create a Settings UI for easy config editing.~~
- ~~Enable Integration with [KillFrenzyAvatarText](https://github.com/killfrenzy96/KillFrenzyAvatarText).~~
- Transcribe continuously until the user stops talking.
- Add an emote feature
- ~~Transcribe continuously until the user stops talking.~~
- ~~Add an emote feature~~
- Demo Gif/Video
- Implement Text To Speech

Expand Down

0 comments on commit 49af12b

Please sign in to comment.