mirror of
https://github.com/ggerganov/whisper.cpp.git
synced 2024-11-07 08:34:37 +01:00
speak
scripts for Windows
This commit is contained in:
parent
3f7436e8a0
commit
5b9e59bc07
@ -42,8 +42,8 @@ Example usage:
|
||||
## TTS
|
||||
|
||||
For best experience, this example needs a TTS tool to convert the generated text responses to voice.
|
||||
You can use any TTS engine that you would like - simply edit the [speak.sh](speak.sh) script to your needs.
|
||||
By default, it is configured to use MacOS's `say`, but you can use whatever you wish.
|
||||
You can use any TTS engine that you would like - simply edit the [speak](speak) script to your needs.
|
||||
By default, it is configured to use MacOS's `say` or Windows SpeechSynthesizer, but you can use whatever you wish.
|
||||
|
||||
## Discussion
|
||||
|
||||
|
0
examples/talk-llama/speak.sh → examples/talk-llama/speak
Executable file → Normal file
0
examples/talk-llama/speak.sh → examples/talk-llama/speak
Executable file → Normal file
1
examples/talk-llama/speak.bat
Normal file
1
examples/talk-llama/speak.bat
Normal file
@ -0,0 +1 @@
|
||||
@powershell -ExecutionPolicy Bypass -F examples\talk\speak.ps1 %1 %2
|
12
examples/talk-llama/speak.ps1
Normal file
12
examples/talk-llama/speak.ps1
Normal file
@ -0,0 +1,12 @@
|
||||
# Set-ExecutionPolicy -ExecutionPolicy Bypass -Scope CurrentUser
|
||||
param(
|
||||
# voice options are David or Zira
|
||||
[Parameter(Mandatory=$true)][string]$voice,
|
||||
[Parameter(Mandatory=$true)][string]$text
|
||||
)
|
||||
|
||||
Add-Type -AssemblyName System.Speech;
|
||||
$speak = New-Object System.Speech.Synthesis.SpeechSynthesizer;
|
||||
$speak.SelectVoice("Microsoft $voice Desktop");
|
||||
$speak.Rate="0";
|
||||
$speak.Speak($text);
|
@ -47,7 +47,7 @@ struct whisper_params {
|
||||
std::string language = "en";
|
||||
std::string model_wsp = "models/ggml-base.en.bin";
|
||||
std::string model_llama = "models/ggml-llama-7B.bin";
|
||||
std::string speak = "./examples/talk-llama/speak.sh";
|
||||
std::string speak = "./examples/talk-llama/speak";
|
||||
std::string prompt = "";
|
||||
std::string fname_out;
|
||||
std::string path_session = ""; // path to file for saving/loading model eval state
|
||||
|
@ -37,5 +37,5 @@ wget --quiet --show-progress -O models/ggml-gpt-2-117M.bin https://huggingface.c
|
||||
## TTS
|
||||
|
||||
For best experience, this example needs a TTS tool to convert the generated text responses to voice.
|
||||
You can use any TTS engine that you would like - simply edit the [speak.sh](speak.sh) script to your needs.
|
||||
By default, it is configured to use `espeak`, but you can use whatever you wish.
|
||||
You can use any TTS engine that you would like - simply edit the [speak](speak) script to your needs.
|
||||
By default, it is configured to use MacOS's `say` or `espeak` or Windows SpeechSynthesizer, but you can use whatever you wish.
|
||||
|
2
examples/talk/speak.sh → examples/talk/speak
Executable file → Normal file
2
examples/talk/speak.sh → examples/talk/speak
Executable file → Normal file
@ -15,7 +15,7 @@ say "$2"
|
||||
# Eleven Labs
|
||||
# To use it, install the elevenlabs module from pip (pip install elevenlabs)
|
||||
# It's possible to use the API for free with limited number of characters. To increase this limit register to https://beta.elevenlabs.io to get an api key and paste it after 'ELEVEN_API_KEY='
|
||||
#Keep the line commented to use the free version whitout api key
|
||||
#Keep the line commented to use the free version without api key
|
||||
#
|
||||
#export ELEVEN_API_KEY=your_api_key
|
||||
#wd=$(dirname $0)
|
1
examples/talk/speak.bat
Normal file
1
examples/talk/speak.bat
Normal file
@ -0,0 +1 @@
|
||||
@powershell -ExecutionPolicy Bypass -F examples\talk\speak.ps1 %1 %2
|
12
examples/talk/speak.ps1
Normal file
12
examples/talk/speak.ps1
Normal file
@ -0,0 +1,12 @@
|
||||
# Set-ExecutionPolicy -ExecutionPolicy Bypass -Scope CurrentUser
|
||||
param(
|
||||
# voice options are David or Zira
|
||||
[Parameter(Mandatory=$true)][string]$voice,
|
||||
[Parameter(Mandatory=$true)][string]$text
|
||||
)
|
||||
|
||||
Add-Type -AssemblyName System.Speech;
|
||||
$speak = New-Object System.Speech.Synthesis.SpeechSynthesizer;
|
||||
$speak.SelectVoice("Microsoft $voice Desktop");
|
||||
$speak.Rate="0";
|
||||
$speak.Speak($text);
|
@ -36,7 +36,7 @@ struct whisper_params {
|
||||
std::string language = "en";
|
||||
std::string model_wsp = "models/ggml-base.en.bin";
|
||||
std::string model_gpt = "models/ggml-gpt-2-117M.bin";
|
||||
std::string speak = "./examples/talk/speak.sh";
|
||||
std::string speak = "./examples/talk/speak";
|
||||
std::string fname_out;
|
||||
};
|
||||
|
||||
|
Loading…
Reference in New Issue
Block a user