Downloads · 30 days
124
46% of all-time downloads
gcoli/whisper-large-v3-swiss-german-gguf-q4_0
whisper-large-v3-swiss-german-gguf-q4_0 is a automatic speech recognition model from gcoli. Use it when you need speech turned into text. It is set up for transcribe.cpp. The card lists the license as other.
Provenance: this checkpoint is openai/whisper-large-v3 with the LoRA adapter Flurin17/whisper-large-v3-peft-swiss-german merged into the weights (see mergeprovenance.json). The licence terms of that adapter and its tr…
Downloads · 30 days
124
46% of all-time downloads
All-time downloads
270
Public
Repo size
902 MB
Likes
0
Public
Click a slice to open those files.
.gguf902 MB · 100%
From the Hugging Face model README
Provenance: this checkpoint is
openai/whisper-large-v3with the LoRA adapterFlurin17/whisper-large-v3-peft-swiss-germanmerged into the weights (seemerge_provenance.json). The licence terms of that adapter and its training data apply.
Q4_0-quantized GGUF conversion of openai/whisper-large-v3 with the LoRA
adapter Flurin17/whisper-large-v3-peft-swiss-german merged into the weights.
This is a standalone checkpoint for
handy-computer/transcribe.cpp.
ffmpeg -i input.m4a -ar 16000 -ac 1 input.wav
build/bin/transcribe-cli \
-m whisper-large-v3-swiss-german-Q4_0.gguf \
--language de \
input.wav
For Swiss German transcription, de is the recommended Whisper language token
and transcribe is the intended task.
handy-computer/transcribe.cppUse
gcoli/whisper-large-v3-swiss-german-mlx-fp16
for oMLX.
1ecca609f9a5ae2cd97a576a9725bc714c022a932ae117cf342bc57d6068066181a9d359e98a2961transcribe.cpp converter and quantizer revision:
856d7c10a1a864b900e066b7c9801edf373f5148Q4_0The adapter was merged into the base model in FP16. The resulting F16 GGUF was
then quantized using transcribe-quantize. Tokenizer, frontend and model
metadata remain embedded in the GGUF. quantization_provenance.json records
the exact F16 source checksum.
The build performs checksum validation and a real runtime transcription test. Independent Swiss German WER and controlled performance comparisons between F16, Q8_0 and Q4_0 have not yet been published. Q4_0 trades a smaller model and lower memory demand for a potentially larger accuracy loss than Q8_0.
Whisper can hallucinate or omit text, particularly with noise, silence, overlapping speakers, uncommon dialects, or specialized vocabulary. Do not use its output as the sole basis for high-impact decisions.
SwissDial CC BY-NC 4.0 with no-reidentification condition
The Swiss German adaptation was trained on the SwissDial dataset. Use is limited to non-commercial purposes under CC BY-NC 4.0, attempts to re-identify SwissDial speakers are prohibited, and SwissDial must be attributed and cited in research use.
The Whisper base model remains subject to Apache-2.0. This repository grants no additional rights to upstream models, training data, or software.