Spaces:

Luigi
/

tiny-scribe

Running

App Files Files Community

138 kB

Ctrl+K

Ctrl+K

2 contributors

History: 81 commits

Luigi's picture

feat: Add GLM-4.7-Flash-30B (Original) IQ2_XXS 2-bit quantization

5c93b30 3 months ago

.gitattributes

302 Bytes
Add HuggingFace Spaces demo with Gradio UI 3 months ago
.gitignore

507 Bytes
Exclude transcripts from HF Spaces deployment 3 months ago
.gitmodules

108 Bytes
add llama-cpp-python JamePeng's fork 3 months ago
AGENTS.md

6.32 kB
Add bilingual support: English and Traditional Chinese (zh-TW) 3 months ago
BENCHMARK_SUMMARY.txt

7.07 kB
comprehensive model benchmark: 6 models evaluated for transcript summarization 3 months ago
CLAUDE.md

11.1 kB
Update CLAUDE.md with current implementation details 3 months ago
DEPLOY.md

4.62 kB
Test: Verify git workflow preserves commit messages 3 months ago
Dockerfile

957 Bytes
Invalidate Docker cache to force fresh app.py copy 3 months ago
FINAL_BENCHMARK_REPORT.txt

8.24 kB
comprehensive model benchmark: 6 models evaluated for transcript summarization 3 months ago
README.md

4.95 kB
feat: Add GLM-4.7-Flash-30B (Original) IQ2_XXS 2-bit quantization 3 months ago
app.py

45.5 kB
feat: Add GLM-4.7-Flash-30B (Original) IQ2_XXS 2-bit quantization 3 months ago
deploy.sh

2.7 kB
Test: Verify git workflow preserves commit messages 3 months ago
model_benchmark_report.md

11.2 kB
comprehensive model benchmark: 6 models evaluated for transcript summarization 3 months ago
model_comparison.md

4.36 kB
comprehensive model benchmark: 6 models evaluated for transcript summarization 3 months ago
requirements.txt

73 Bytes
Use prebuilt llama-cpp-python wheel for faster builds 3 months ago
summarize_transcript.py

6.65 kB
Add bilingual support: English and Traditional Chinese (zh-TW) 3 months ago
summary_20260201_121726.json

3.56 kB
fix: Download button now works - removed broken .then() chain 3 months ago
summary_evaluation.md

5.62 kB
comprehensive model benchmark: 6 models evaluated for transcript summarization 3 months ago
summary_granite.txt

1.56 kB
comprehensive model benchmark: 6 models evaluated for transcript summarization 3 months ago
summary_granite_tiny.txt

1.62 kB
comprehensive model benchmark: 6 models evaluated for transcript summarization 3 months ago
summary_lfm2.txt

1.52 kB
comprehensive model benchmark: 6 models evaluated for transcript summarization 3 months ago
summary_qwen2.txt

1.52 kB
comprehensive model benchmark: 6 models evaluated for transcript summarization 3 months ago
thinking_granite.txt

1.99 kB
comprehensive model benchmark: 6 models evaluated for transcript summarization 3 months ago
thinking_granite_tiny.txt

1.99 kB
comprehensive model benchmark: 6 models evaluated for transcript summarization 3 months ago
thinking_lfm2.txt

1.99 kB
comprehensive model benchmark: 6 models evaluated for transcript summarization 3 months ago
thinking_qwen2.txt

1.99 kB
comprehensive model benchmark: 6 models evaluated for transcript summarization 3 months ago