public_git
/
whisper.cpp
mirror of https://github.com/ggml-org/whisper.cpp.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

examples : update model names in parakeet-cli README.md [no ci] (#3906) 

This commit updates the parakeet model names which are currently missing
the 'ggml-' prefix.
This commit is contained in:
Daniel Bevenius 2026-06-23 09:12:31 +02:00 committed by GitHub
parent bae6bc02b1
commit 43d78af5be
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 3 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
examples/parakeet-cli/README.md
View File

@ -4,7 +4,7 @@ This is an example of using the [Parakeet] model in whisper.cpp.
### Download converted model ### Download converted model
```console ```console
$ hf download ggml-org/parakeet-GGUF parakeet-tdt-0.6b-v3-f16.bin --local-dir models $ hf download ggml-org/parakeet-GGUF ggml-parakeet-tdt-0.6b-v3-f16.bin --local-dir models
``` ```
### Building ### Building
@ -32,7 +32,7 @@ options:
### Example ### Example
```console ```console
$ ./build/bin/parakeet-cli -m models/parakeet-tdt-0.6b-v3-f16.bin -f samples/jfk.wav $ ./build/bin/parakeet-cli -m models/ggml-parakeet-tdt-0.6b-v3-f16.bin -f samples/jfk.wav
Processing audio (176000 samples, 11.00 seconds) Processing audio (176000 samples, 11.00 seconds)
Processing audio: total_frames=1101, chunk_size=1101 Processing audio: total_frames=1101, chunk_size=1101
parakeet_decode: starting decode with n_frames=138 parakeet_decode: starting decode with n_frames=138
@ -41,7 +41,7 @@ And so, my fellow Americans, ask not what your country can do for you, ask what
To print segment information: To print segment information:
```console ```console
$ ./build/bin/parakeet-cli -m models/parakeet-tdt-0.6b-v3-f16.bin -f samples/jfk.wav --print-segments $ ./build/bin/parakeet-cli -m models/ggml-parakeet-tdt-0.6b-v3-f16.bin -f samples/jfk.wav --print-segments
Processing audio (176000 samples, 11.00 seconds) Processing audio (176000 samples, 11.00 seconds)
Processing audio: total_frames=1101, chunk_size=1101 Processing audio: total_frames=1101, chunk_size=1101
parakeet_decode: starting decode with n_frames=138 parakeet_decode: starting decode with n_frames=138