We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
suggestion is to Implement -float-stream option for whisper-cli simplifying and enabling infinite streams
The simplest ingestion is by raw PCM samples read from standard input of a convention format
ffmpeg -hide_banner -i i.mp4 -ac 1 -ar 16k -f f32le - | whisper-cli -float-stream --model ggml-large-v3-turbo.bin… | myTextConsumer
a raw PCM stream is easily produced by upstream software enabling mixing, file sequencing and infinite streams
.
ffmpeg produces samples within 3 s for 5 h file which otherwise takes 10 minutes to create wav headers
whisper-cli ingestion reads 30 s of samples at a time until EOF
always 32-bit float little endian 16 kHz
ffmpeg is unavoidable to allow for any file format to be output in specific sample format
The text was updated successfully, but these errors were encountered:
No branches or pull requests
suggestion is to Implement -float-stream option for whisper-cli simplifying and enabling infinite streams
The simplest ingestion is by raw PCM samples read from standard input of a convention format
a raw PCM stream is easily produced by upstream software enabling mixing, file sequencing and infinite streams
.
ffmpeg produces samples within 3 s for 5 h file which otherwise takes 10 minutes to create wav headers
.
whisper-cli ingestion reads 30 s of samples at a time until EOF
always 32-bit float little endian 16 kHz
.
ffmpeg is unavoidable to allow for any file format to be output in specific sample format
The text was updated successfully, but these errors were encountered: