admin
03bc6b1d90
Document and preserve the controlled Progeo benchmark series. Whisper comparison: - Compare whisper.cpp large-v3 and large-v3-turbo - Identify and verify BUG-012: extraction stability depends on chunk size - Repeat both transcription variants with identical reduced chunk budgets - Select large-v3-turbo as the current production transcription model LLM comparison: - Compare qwen3.5:9b with qwen3.5:35B-A3B - Preserve identical transcript, Meeting Context, prompts and chunking - Retain qwen3.5:9b as the production recommendation - Record runtime, repair burden and semantic-quality findings Current production benchmark configuration: - whisper.cpp large-v3-turbo - target_chars=4500 - max_chars=5500 - min_chars=2500 - overlap_blocks=0 - qwen3.5:9b - num_ctx=32768 - think=false - temperature=0 BUG-012 remains verified but not yet fixed in the production chunker.
87 lines
1.8 KiB
JSON
87 lines
1.8 KiB
JSON
{
|
|
"source_file": "progeo_whispercpp_vulkan_turbo_trimmed_converted.json",
|
|
"chunk_count": 10,
|
|
"chunks": [
|
|
{
|
|
"number": 1,
|
|
"filename": "chunk_01.txt",
|
|
"chars": 9077,
|
|
"blocks": 125,
|
|
"first_timestamp": null,
|
|
"last_timestamp": null
|
|
},
|
|
{
|
|
"number": 2,
|
|
"filename": "chunk_02.txt",
|
|
"chars": 9053,
|
|
"blocks": 103,
|
|
"first_timestamp": null,
|
|
"last_timestamp": null
|
|
},
|
|
{
|
|
"number": 3,
|
|
"filename": "chunk_03.txt",
|
|
"chars": 9053,
|
|
"blocks": 106,
|
|
"first_timestamp": null,
|
|
"last_timestamp": null
|
|
},
|
|
{
|
|
"number": 4,
|
|
"filename": "chunk_04.txt",
|
|
"chars": 9004,
|
|
"blocks": 126,
|
|
"first_timestamp": null,
|
|
"last_timestamp": null
|
|
},
|
|
{
|
|
"number": 5,
|
|
"filename": "chunk_05.txt",
|
|
"chars": 9015,
|
|
"blocks": 117,
|
|
"first_timestamp": null,
|
|
"last_timestamp": null
|
|
},
|
|
{
|
|
"number": 6,
|
|
"filename": "chunk_06.txt",
|
|
"chars": 9026,
|
|
"blocks": 107,
|
|
"first_timestamp": null,
|
|
"last_timestamp": null
|
|
},
|
|
{
|
|
"number": 7,
|
|
"filename": "chunk_07.txt",
|
|
"chars": 9008,
|
|
"blocks": 126,
|
|
"first_timestamp": null,
|
|
"last_timestamp": null
|
|
},
|
|
{
|
|
"number": 8,
|
|
"filename": "chunk_08.txt",
|
|
"chars": 9118,
|
|
"blocks": 145,
|
|
"first_timestamp": null,
|
|
"last_timestamp": null
|
|
},
|
|
{
|
|
"number": 9,
|
|
"filename": "chunk_09.txt",
|
|
"chars": 8483,
|
|
"blocks": 165,
|
|
"first_timestamp": null,
|
|
"last_timestamp": null
|
|
},
|
|
{
|
|
"number": 10,
|
|
"filename": "chunk_10.txt",
|
|
"chars": 5048,
|
|
"blocks": 91,
|
|
"first_timestamp": null,
|
|
"last_timestamp": null
|
|
}
|
|
]
|
|
}
|