femustafa/voicedictation-models

VoiceDictation Roman-Urdu GGML models

whisper.cpp (GGML) conversions of the cheetos18/whisper-small-roman-urdu fine-tune, built for the VoiceDictation Android app's on-device Roman-Urdu dictation.

The upstream repo hosts the Transformers/safetensors checkpoint; this repo hosts the same model converted to the GGML .bin format that whisper.cpp consumes, so the app can download it directly at runtime.

Files

File	Format	Size	Notes
ggml-model-q4_0.bin	q4_0 quantized	~139 MB	Default: fastest on device
ggml-model-f16.bin	f16	~466 MB	Unquantized: higher quality

Model is small (n_vocab 51865), multilingual.

Usage

whisper-cli -m ggml-model-q4_0.bin -f audio.wav -l auto

Important: always run with language auto-detect (-l auto), NEVER force -l ur. Forcing the native language token leaks native-script (Urdu-script) output; -l auto keeps the transcript in clean Roman/Latin script.

Derivation

• Source: cheetos18/whisper-small-roman-urdu (model.safetensors, verified)
• Conversion: convert-h5-to-ggml.py (whisper.cpp legacy converter)
• Quantization: whisper-quantize ggml-model.bin ggml-model-q4_0.bin q4_0
• Verified: both files transcribe a Roman-Urdu clip as aap ka kya haal hai? under -l auto.