ggml-org/whisper.cpp

Pattern Findings

953 matches across 15 categories. Click a row to expand file-level details.

Over-Commented Block816 hits · 727 pts

Severity	File	Line	Snippet
LOW	CMakeLists.txt	141	else()
LOW	ci/run.sh	1	#!/bin/bash
LOW	include/whisper.h	1	#ifndef WHISPER_H
LOW	include/whisper.h	21	# ifdef WHISPER_BUILD
LOW	include/whisper.h	41
LOW	include/whisper.h	61	// }
LOW	include/whisper.h	241	WHISPER_API struct whisper_state * whisper_init_state(struct whisper_context * ctx);
LOW	include/whisper.h	361	// Examples:
LOW	tests/run-tests.sh	1	#!/bin/bash
LOW	tests/test-vad-full.cpp	1	#include "whisper.h"
LOW	models/convert-h5-to-ggml.py	1	# Convert Hugging Face fine-tuned models to ggml format
LOW	models/convert-pt-to-ggml.py	1	# Convert Whisper transformer model from PyTorch to ggml format
LOW	models/convert-pt-to-ggml.py	21	# - mel filters
LOW	models/convert-pt-to-ggml.py	41	import numpy as np
LOW	models/convert-pt-to-ggml.py	61	# "nl": "dutch",
LOW	models/convert-pt-to-ggml.py	81	# "hr": "croatian",
LOW	models/convert-pt-to-ggml.py	101	# "is": "icelandic",
LOW	models/convert-pt-to-ggml.py	121	# "tg": "tajik",
LOW	models/convert-pt-to-ggml.py	141	# "tt": "tatar",
LOW	examples/grammar-parser.h	1	// Implements a parser for an extended Backus-Naur form (BNF), producing the
LOW	examples/json.hpp	21	#include <algorithm> // all_of, find, for_each
LOW	examples/json.hpp	41	// SPDX-FileCopyrightText: 2013-2022 Niels Lohmann <https://nlohmann.me>
LOW	examples/json.hpp	61	#ifndef JSON_SKIP_LIBRARY_VERSION_CHECK
LOW	examples/json.hpp	81	#if JSON_DIAGNOSTICS
LOW	examples/json.hpp	141	{
LOW	examples/json.hpp	161	#include <algorithm> // transform
LOW	examples/json.hpp	181
LOW	examples/json.hpp	201	#include <array> // array
LOW	examples/json.hpp	221	// \| \| \|__ \| \| \| \| \| \| version 3.11.2
LOW	examples/json.hpp	321	// \| \| \|__ \| \| \| \| \| \| version 3.11.2
LOW	examples/json.hpp	341	#define JSON_HEDLEY_STRINGIFY_EX(x) #x
LOW	examples/json.hpp	361	#define JSON_HEDLEY_CONCAT3_EX(a,b,c) a##b##c
LOW	examples/json.hpp	381	#define JSON_HEDLEY_VERSION_DECODE_MINOR(version) (((version) % 1000000) / 1000)
LOW	examples/json.hpp	401	#define JSON_HEDLEY_GNUC_VERSION_CHECK(major,minor,patch) (JSON_HEDLEY_GNUC_VERSION >= JSON_HEDLEY_VERSION_ENCODE(ma
LOW	examples/json.hpp	421	#define JSON_HEDLEY_MSVC_VERSION_CHECK(major,minor,patch) (0)
LOW	examples/json.hpp	441	#endif
LOW	examples/json.hpp	461	#define JSON_HEDLEY_INTEL_CL_VERSION_CHECK(major,minor,patch) (0)
LOW	examples/json.hpp	481	#undef JSON_HEDLEY_SUNPRO_VERSION
LOW	examples/json.hpp	501
LOW	examples/json.hpp	521	#if defined(__CC_ARM) && defined(__ARMCOMPILER_VERSION)
LOW	examples/json.hpp	541	#elif defined(__xlC__) && defined(__xlC_ver__)
LOW	examples/json.hpp	561	( \
LOW	examples/json.hpp	581	#undef JSON_HEDLEY_TI_CL2000_VERSION
LOW	examples/json.hpp	601	#endif
LOW	examples/json.hpp	621	#endif
LOW	examples/json.hpp	641	#define JSON_HEDLEY_TI_CL6X_VERSION_CHECK(major,minor,patch) (0)
LOW	examples/json.hpp	661	#undef JSON_HEDLEY_TI_CLPRU_VERSION
LOW	examples/json.hpp	681	#define JSON_HEDLEY_CRAY_VERSION JSON_HEDLEY_VERSION_ENCODE(_RELEASE_MAJOR, _RELEASE_MINOR, _RELEASE_PATCHLEVEL)
LOW	examples/json.hpp	701	#define JSON_HEDLEY_IAR_VERSION JSON_HEDLEY_VERSION_ENCODE((__VER__ / 1000000), ((__VER__ / 1000) % 1000), (__VE
LOW	examples/json.hpp	721	#endif
LOW	examples/json.hpp	741	#endif
LOW	examples/json.hpp	761	#define JSON_HEDLEY_COMPCERT_VERSION_CHECK(major,minor,patch) (0)
LOW	examples/json.hpp	781	#undef JSON_HEDLEY_MCST_LCC_VERSION
LOW	examples/json.hpp	821	#if defined(JSON_HEDLEY_GCC_VERSION)
LOW	examples/json.hpp	841	#undef JSON_HEDLEY_GNUC_HAS_ATTRIBUTE
LOW	examples/json.hpp	861	#if \
LOW	examples/json.hpp	881	#else
LOW	examples/json.hpp	901	#endif
LOW	examples/json.hpp	921	#if defined(JSON_HEDLEY_GCC_HAS_BUILTIN)
LOW	examples/json.hpp	941	#endif
756 more matches not shown…

Redundant / Tautological Comments34 hits · 66 pts

Severity	File	Line	Snippet
LOW	models/convert-silero-vad-to-ggml.py	146	# Check if this is a convolution weight tensor
LOW	models/download-ggml-model.sh	27	# Check if the script is inside a /bin/ directory
LOW	models/download-ggml-model.sh	137	# Check if 'whisper-cli' is available in the system PATH
LOW	models/download-coreml-model.sh	24	# Check if the script is inside a /bin/ directory
LOW	models/download-coreml-model.sh	88	# Check if 'whisper-cli' is available in the system PATH
LOW	models/download-vad-model.sh	24	# Check if the script is inside a /bin/ directory
LOW	models/download-vad-model.sh	93	# Check if 'whisper-cli' is available in the system PATH
LOW	examples/server.py	60	# Check if this is a request to a file in whisper.wasm
LOW	examples/python/whisper_processor.py	17	# Check if the file exists
LOW	scripts/bench.py	128	# Check if the sample file exists
LOW	scripts/apple/validate-macos.sh	685	# Check if authentication credentials are provided
LOW	scripts/apple/validate-macos.sh	704	# Check if app was created successfully
LOW	scripts/apple/validate-macos.sh	712	# Check if app binary exists and is executable
LOW	scripts/apple/validate-macos.sh	720	# Check if framework was properly embedded
LOW	scripts/apple/validate-macos.sh	728	# Check if framework binary exists
LOW	scripts/apple/validate-visionos.sh	679	# Check if authentication credentials are provided
LOW	scripts/apple/validate-visionos.sh	704	# Check if validation failed because the app isn't in App Store Connect
LOW	scripts/apple/validate-visionos.sh	713	# Check if IPA was created successfully
LOW	scripts/apple/validate-visionos.sh	721	# Check if app binary exists and is executable
LOW	scripts/apple/validate-visionos.sh	729	# Check if framework was properly embedded
LOW	scripts/apple/validate-visionos.sh	737	# Check if framework binary exists
LOW	scripts/apple/validate-ios.sh	688	# Check if authentication credentials are provided
LOW	scripts/apple/validate-ios.sh	713	# Check if validation failed because the app isn't in App Store Connect
LOW	scripts/apple/validate-ios.sh	722	# Check if IPA was created successfully
LOW	scripts/apple/validate-ios.sh	730	# Check if app binary exists and is executable
LOW	scripts/apple/validate-ios.sh	738	# Check if framework was properly embedded
LOW	scripts/apple/validate-ios.sh	746	# Check if framework binary exists
LOW	scripts/apple/validate-tvos.sh	681	# Check if authentication credentials are provided
LOW	scripts/apple/validate-tvos.sh	706	# Check if validation failed because the app isn't in App Store Connect
LOW	scripts/apple/validate-tvos.sh	715	# Check if IPA was created successfully
LOW	scripts/apple/validate-tvos.sh	723	# Check if app binary exists and is executable
LOW	scripts/apple/validate-tvos.sh	731	# Check if framework was properly embedded
LOW	scripts/apple/validate-tvos.sh	739	# Check if framework binary exists
LOW	ggml/src/ggml-virtgpu/regenerate_remoting.py	46	# Check if clang-format is available

Self-Referential Comments11 hits · 33 pts

Severity	File	Line	Snippet
MEDIUM	build-xcframework.sh	384	# Create a separate directory for dSYMs for all platforms
MEDIUM	build-xcframework.sh	392	# Create a copy of the binary that will be stripped
MEDIUM	scripts/bench.py	18	# Define the argument to accept a list
MEDIUM	scripts/bench.py	54	# Define the models, threads, and processor counts to benchmark
MEDIUM	scripts/apple/validate-macos.sh	571	# Create a simple xcscheme file to avoid xcodebuild scheme issues
MEDIUM	scripts/apple/validate-macos.sh	667	# Create a zip file for potential distribution
MEDIUM	scripts/apple/validate-visionos.sh	565	# Create a simple xcscheme file to avoid xcodebuild scheme issues
MEDIUM	scripts/apple/validate-ios.sh	574	# Create a simple xcscheme file to avoid xcodebuild scheme issues
MEDIUM	scripts/apple/validate-tvos.sh	567	# Create a simple xcscheme file to avoid xcodebuild scheme issues
MEDIUM	.github/workflows/build.yml	838	# Create the directory where the CUDA Toolkit will be installed
MEDIUM	.github/workflows/build.yml	894	# Create the directory where the CUDA Toolkit will be installed

Verbosity Indicators20 hits · 30 pts

Severity	File	Line	Snippet
LOW	examples/talk-llama/llama-sampler.cpp	2947	// Step 1: Look for restart sequences to limit the maximum repetition length.
LOW	examples/talk-llama/llama-sampler.cpp	3008	// Step 2: Iterate in reverse over the last N tokens of the context, using the "Z-algorithm" (in
LOW	examples/talk-llama/llama-sampler.cpp	3072	// Step 3: Iterate over dry_repeat_count and last_tokens, examining the maximum repeat length
LOW	examples/talk-llama/llama-sampler.cpp	3099	// Step 4: Apply logit penalties based on the maximum repeat length for relevant tokens.
LOW	examples/talk-llama/models/kimi-linear.cpp	197	// Step 1: Q, K, V projections -> [d_inner, n_tokens]
LOW	examples/talk-llama/models/kimi-linear.cpp	377	// Step 1: Q projection and reshape
LOW	examples/talk-llama/models/kimi-linear.cpp	382	// Step 2: KV compression
LOW	ggml/src/ggml-webgpu/ggml-webgpu.cpp	1290	// For set rows specifically, we need to check if src and idx are empty
LOW	ggml/src/ggml-cann/aclnn_ops.cpp	2809	// Step 5: multiply by attn_factor
LOW	ggml/src/ggml-cann/aclnn_ops.cpp	2826	// Step 6: repeat
LOW	ggml/src/ggml-cann/aclnn_ops.cpp	3090	// Step 1: Prepare trans tensors for F16 type conversion to F32 if needed
LOW	ggml/src/ggml-cann/aclnn_ops.cpp	3115	// Step 2: Prepare head tensors for tail splitting if needed
LOW	ggml/src/ggml-cann/aclnn_ops.cpp	3144	// Step 3: Execute RotaryPositionEmbedding
LOW	ggml/src/ggml-cann/aclnn_ops.cpp	3191	// Step 4: Copy unrotated tail portion from source to destination
LOW	ggml/src/ggml-cann/aclnn_ops.cpp	3220	// Step 5: Cast back to F16 if needed
LOW	ggml/src/ggml-cann/aclnn_ops.cpp	3906	// Step 1: cast the src0 (Query) to fp16 if needed
LOW	ggml/src/ggml-cann/aclnn_ops.cpp	3929	// Step 2: create the acl tensors for src1 (Key), src2 (Value),
LOW	ggml/src/ggml-cann/aclnn_ops.cpp	3973	// Step 3: create the PSEShift tensor if needed
LOW	ggml/src/ggml-cann/aclnn_ops.cpp	4042	// Step 4: set the inputs for FusedInferAttention.
LOW	ggml/src/ggml-cann/aclnn_ops.cpp	4103	// Step 6: post-processing — slice padded output and/or cast to f32

AI Slop Vocabulary8 hits · 24 pts

Severity	File	Line	Snippet
MEDIUM	examples/stb_vorbis.c	51	// 1.10 - 2017-03-03 - more robust seeking; fix negative ilog(); clear error in open_memory
MEDIUM	ggml/src/ggml-zendnn/ggml-zendnn.cpp	600	// gather + batched matmul + scatter approach. Future versions will leverage
MEDIUM	ggml/src/ggml-cpu/amx/mmq.cpp	603	// pack again with 128 to fully utilize vector length
MEDIUM	ggml/src/ggml-cpu/amx/mmq.cpp	645	// pack again with 128 to fully utilize vector length
MEDIUM	ggml/src/ggml-cpu/amx/mmq.cpp	743	// pack again with 128 to fully utilize vector length
MEDIUM	ggml/src/ggml-opencl/ggml-opencl.cpp	4396	// that wraps around q and d to utilize image access path.
MEDIUM	ggml/src/ggml-opencl/ggml-opencl.cpp	4430	// that wraps around q and d to utilize image access path.
MEDIUM	src/whisper.cpp	8371	// guaranteed. Might get removed at some point unless a robust algorithm implementation is found

Excessive Try-Catch Wrapping14 hits · 22 pts

Severity	File	Line	Snippet
LOW	models/convert-pt-to-ggml.py	206	except Exception:
MEDIUM	models/convert-pt-to-ggml.py	207	print("Error: failed to load PyTorch model file:" , fname_inp)
MEDIUM	models/convert-pt-to-ggml.py	238	print("Error: failed to find either tiktoken or hf_transformers tokenizer file:", tokenizer)
MEDIUM	examples/server.py	119	print(f"Error: {e}")
LOW	examples/python/test_whisper_processor.py	6	except Exception as e:
MEDIUM	examples/python/test_whisper_processor.py	7	print(f"Error: {e}")
LOW	examples/python/whisper_processor.py	48	except Exception as e:
MEDIUM	examples/python/whisper_processor.py	49	print(f"Error: {e}")
MEDIUM	…r.swiftui/whisper.swiftui.demo/UI/DownloadButton.swift	32	print("Error: \(error.localizedDescription)")
MEDIUM	…r.swiftui/whisper.swiftui.demo/UI/DownloadButton.swift	48	print("Error: \(err.localizedDescription)")
MEDIUM	…r.swiftui/whisper.swiftui.demo/UI/DownloadButton.swift	90	print("Error deleting file: \(error)")
LOW	ggml/src/ggml-virtgpu/regenerate_remoting.py	69	except Exception as e:
LOW	ggml/src/ggml-virtgpu/regenerate_remoting.py	327	except Exception as e:
MEDIUM	ggml/src/ggml-virtgpu/regenerate_remoting.py	323	def main():

Hyper-Verbose Identifiers19 hits · 20 pts

Severity	File	Line	Snippet
LOW	tests/earnings21/normalizers/basic.py	27	def remove_symbols_and_diacritics(s: str, keep=""):
LOW	tests/librispeech/normalizers/basic.py	27	def remove_symbols_and_diacritics(s: str, keep=""):
LOW	models/convert-whisper-to-coreml.py	38	def correct_for_bias_scale_order_inversion(state_dict, prefix, local_metadata,
LOW	examples/server.py	15	class CustomHTTPRequestHandler(http.server.SimpleHTTPRequestHandler):
LOW	…/wchess.wasm/chessboardjs-1.0.0/js/chessboard-1.0.0.js	496	function calculatePositionFromMoves (position, moves) {
LOW	…/wchess.wasm/chessboardjs-1.0.0/js/chessboard-1.0.0.js	541	function expandConfigArgumentShorthand (config) {
LOW	…/wchess.wasm/chessboardjs-1.0.0/js/chessboard-1.0.0.js	951	function animateSparePieceToSquare (piece, dest, completeFn) {
LOW	bindings/javascript/whisper.js	8	function GROWABLE_HEAP_I8(){if(wasmMemory.buffer!=HEAP8.buffer){updateMemoryViews()}return HEAP8}function GROWABLE_HEAP_
LOW	bindings/ruby/test/test_context_params.rb	60	def test_new_with_kw_args_default_values(param)
LOW	bindings/ruby/test/test_vad_params.rb	83	def test_new_with_kw_args_default_values(param)
LOW	bindings/ruby/test/test_params.rb	278	def test_new_with_kw_args_default_values(param)
LOW	ggml/include/ggml-backend.h	211	typedef ggml_backend_buffer_type_t (ggml_backend_split_buffer_type_t)(int main_device, const float tensor_split
LOW	ggml/src/ggml-virtgpu/regenerate_remoting.py	49	def _check_clang_format_available(self) -> bool:
LOW	ggml/src/ggml-virtgpu/regenerate_remoting.py	53	def _format_file_with_clang_format(self, file_path: Path) -> bool:
LOW	ggml/src/ggml-virtgpu/regenerate_remoting.py	78	def generate_backend_function_name(self, group_name: str, function_name: str) -> str:
LOW	ggml/src/ggml-virtgpu/regenerate_remoting.py	89	def generate_frontend_function_name(self, group_name: str, function_name: str) -> str:
LOW	ggml/src/ggml-virtgpu/regenerate_remoting.py	125	def generate_apir_backend_header(self) -> str:
LOW	ggml/src/ggml-virtgpu/regenerate_remoting.py	176	def generate_backend_dispatched_header(self) -> str:
LOW	ggml/src/ggml-virtgpu/regenerate_remoting.py	222	def generate_virtgpu_forward_header(self) -> str:

Decorative Section Separators4 hits · 18 pts

Severity	File	Line	Snippet
MEDIUM	examples/addon.node/CMakeLists.txt	4	#==================================================================
MEDIUM	examples/addon.node/CMakeLists.txt	8	#==================================================================
MEDIUM	examples/addon.node/CMakeLists.txt	16	#==================================================================
MEDIUM	examples/addon.node/CMakeLists.txt	24	#==================================================================

Synthetic Comment Markers3 hits · 15 pts

Severity	File	Line	Snippet
HIGH	CONTRIBUTING.md	18	Code that is initially generated by AI and subsequently edited will still be considered AI-generated. AI assistance is p
HIGH	ggml/src/ggml-virtgpu/regenerate_remoting.py	3	# Generated by Claude AI
HIGH	ggml/src/ggml-hexagon/ggml-hexagon.cpp	2484	// Check for F16 support only as requested

Unused Imports11 hits · 11 pts

Severity	File	Line
LOW	tests/earnings21/normalizers/__init__.py	1
LOW	tests/earnings21/normalizers/__init__.py	2
LOW	tests/librispeech/normalizers/__init__.py	1
LOW	tests/librispeech/normalizers/__init__.py	2
LOW	models/convert-h5-to-ggml.py	18
LOW	models/convert-h5-to-ggml.py	23
LOW	models/convert-silero-vad-to-ggml.py	4
LOW	models/convert-pt-to-ggml.py	35
LOW	models/convert-pt-to-ggml.py	39
LOW	models/convert-h5-to-coreml.py	13
LOW	examples/server.py	6

Hallucination Indicators1 hit · 10 pts

Severity	File	Line	Snippet
CRITICAL	examples/wchess/wchess.wasm/jquery-3.7.1.min.js	2	!function(e,t){"use strict";"object"==typeof module&&"object"==typeof module.exports?module.exports=e.document?t(e,!0):f

Example Usage Blocks6 hits · 9 pts

Severity	File	Line	Snippet
LOW	tests/run-tests.sh	14	# Usage:
LOW	models/convert-h5-to-ggml.py	3	# Usage:
LOW	examples/generate-karaoke.sh	4	# Usage:
LOW	examples/yt-wsp.sh	31	# Sample usage:
LOW	scripts/sync-ggml-am.sh	5	# Usage:
LOW	ggml/src/ggml-sycl/dpct/helper.hpp	3012	/// Example usage:

Deep Nesting4 hits · 4 pts

Severity	File	Line
LOW	tests/earnings21/normalizers/english.py	165
LOW	tests/librispeech/normalizers/english.py	165
LOW	examples/server.py	19
LOW	ggml/src/ggml-webgpu/wgsl-shaders/embed_wgsl.py	68

Slop Phrases1 hit · 2 pts

Severity	File	Line	Snippet
LOW	tests/run-tests.sh	62	# when adding new files, make sure to add the expected "ref.txt" file with the correct transcript

Overly Generic Function Names1 hit · 1 pts

Severity	File	Line	Snippet
LOW	bindings/javascript/whisper.js	8	function GROWABLE_HEAP_I8(){if(wasmMemory.buffer!=HEAP8.buffer){updateMemoryViews()}return HEAP8}function GROWABLE_HEAP_

Score History

Severity Breakdown

Pattern Findings