Spaces:

build-small-hackathon
/

EuropaLex

Build error

App Files Files Community

EuropaLex / core

Commit History

Jun 14

13:17
docs: removing nemotron and tildeopen model references

Takosaga

480dac5
10:41
feat: lowered inference steps

Takosaga

89d4e63

Jun 13

12:47
feat: A0 removed and default to A2

Takosaga

371681a
11:58
test: remove stale test_text_engine.py (tests deprecated TextEngine class)

Takosaga

be6160e
11:55
refactor: extract TTSEngine and ImageGenEngine from engine.py

Takosaga

16d415a
11:54
feat: extract ImageGenEngine into core/image_gen.py

Takosaga

e967ac3
11:53
feat: extract TTSEngine into core/audio_gen.py

Takosaga

52866c6
11:12
feat: cards work

Takosaga

a5ae514

Jun 12

20:44
fix: more adjustments for images

Takosaga

2e519f3
20:28
fix: image prompt and size

Takosaga

afb56db
20:17
feat: reduce image generation size to 450x300

Takosaga

068b45c
14:36
feat: accept instruct parameter in TTSEngine.synthesize()

Takosaga

e8b001f
11:24
fix: prompt fixes with differing types

Takosaga

31d1a12
10:52
feat: download correct model and creates the audio

Takosaga

4c0a5b0
09:25
feat: wire TTS into Phase 2 pipeline with voice design mode

Takosaga

7f0a02a
09:23
feat: add voice design mode to TTSEngine with female speaking instruction

Takosaga

9796129

Jun 11

20:02
fix: target language and update docs

Takosaga

7cafbcb
19:55
feat: update to use local langaguage and added drop down for more languages

Takosaga

882fce1
19:36
fix: prompt adjustments

Takosaga

c8650b7
19:29
fix: dynamic cefr levels

Takosaga

69f9310
19:19
fix: translation does work

Takosaga

48111a3
18:20
feat: implement pipeline.py Phase 2 translation orchestration

Takosaga

0206b48
18:19
feat: add retry loop to LlamaCppTextEngine for translation validation

Takosaga

75b8aac
17:41
docs: up to date docs with phase one done

Takosaga

c8b7bf2
17:33
feat: phase 1 is good enough

Takosaga

3869ee2
17:09
feat: phase 1 works

Takosaga

a6bf50f
15:02
refactor: delegate MiniCPMTextEngine.generate to core.text_gen.generate_sentences

Takosaga

c0a128b
15:00
feat: add extract_sentences and generate_sentences to core.text_gen

Takosaga

d92213f
14:26
feat: adjusting for type safety

Takosaga

1ff48d6
10:29
feat: wrap MiniCPMTextEngine.generate() in retry loop for exact sentence count enforcement

Takosaga

b655915
10:29
feat: add _validate_lines and _build_retry_prompt helpers to MiniCPMTextEngine

Takosaga

66d9751
06:07
fix: using cuda for llama cpp python

Takosaga

a47ac7b

Jun 10

20:11
feat: replace TextEngine with MiniCPMTextEngine (llama-cpp-python, chat template)

Takosaga

298a4e4
20:10
refactor: rename nemotron_model_path to minicpm_model_path, remove MoE/ubatch params

Takosaga

3888d8c
19:22
feat: better feedback for errors

Takosaga

b13079f
18:59
feat: cli params for moe

Takosaga

ecdc228
18:14
test: add inline tests for TextEngine generation and translation prompts

Takosaga

3e4942f
16:33
fix: comment out tildeopen

Takosaga

d967693
16:29
feat: swap tildeopen for tiny aya water for translation

Takosaga

6cde582

Jun 9

20:05
feat: add EnginePool singleton — manages mutual exclusion between GPU engines

Takosaga

66bf5aa
20:04
feat: add ImageGenEngine — diffusers Flux2KleinPipeline wrapper with lazy load/unload

Takosaga

e23a661
20:03
feat: add TTSEngine — OmniVoice Python package wrapper with lazy load/unload

Takosaga

f95b1b6
20:03
feat: add TextEngine — llama-cli subprocess wrapper for Nemotron and TildeOpen

Takosaga

79eff63
20:02
feat: add Pydantic types for CardData, TextResult, AudioResult, ImageResult, EngineConfig

Takosaga

1661004

Jun 8

14:44
restructure: move app.py to root, replace model submodules with HF Hub download script, add package markers

Takosaga

798b09f

Jun 7

20:53
feat: scaffold repo structure with empty files and headers

Takosaga

9d62a5e

Commit History

Jun 14

docs: removing nemotron and tildeopen model references

feat: lowered inference steps

Jun 13

feat: A0 removed and default to A2

test: remove stale test_text_engine.py (tests deprecated TextEngine class)

refactor: extract TTSEngine and ImageGenEngine from engine.py

feat: extract ImageGenEngine into core/image_gen.py

feat: extract TTSEngine into core/audio_gen.py

feat: cards work

Jun 12

fix: more adjustments for images

fix: image prompt and size

feat: reduce image generation size to 450x300

feat: accept instruct parameter in TTSEngine.synthesize()

fix: prompt fixes with differing types

feat: download correct model and creates the audio

feat: wire TTS into Phase 2 pipeline with voice design mode

feat: add voice design mode to TTSEngine with female speaking instruction

Jun 11

fix: target language and update docs

feat: update to use local langaguage and added drop down for more languages

fix: prompt adjustments

fix: dynamic cefr levels

fix: translation does work

feat: implement pipeline.py Phase 2 translation orchestration

feat: add retry loop to LlamaCppTextEngine for translation validation

docs: up to date docs with phase one done

feat: phase 1 is good enough

feat: phase 1 works

refactor: delegate MiniCPMTextEngine.generate to core.text_gen.generate_sentences

feat: add extract_sentences and generate_sentences to core.text_gen

feat: adjusting for type safety

feat: wrap MiniCPMTextEngine.generate() in retry loop for exact sentence count enforcement

feat: add _validate_lines and _build_retry_prompt helpers to MiniCPMTextEngine

fix: using cuda for llama cpp python

Jun 10

feat: replace TextEngine with MiniCPMTextEngine (llama-cpp-python, chat template)

refactor: rename nemotron_model_path to minicpm_model_path, remove MoE/ubatch params

feat: better feedback for errors

feat: cli params for moe

test: add inline tests for TextEngine generation and translation prompts

fix: comment out tildeopen

feat: swap tildeopen for tiny aya water for translation

Jun 9

feat: add EnginePool singleton — manages mutual exclusion between GPU engines

feat: add ImageGenEngine — diffusers Flux2KleinPipeline wrapper with lazy load/unload

feat: add TTSEngine — OmniVoice Python package wrapper with lazy load/unload

feat: add TextEngine — llama-cli subprocess wrapper for Nemotron and TildeOpen

feat: add Pydantic types for CardData, TextResult, AudioResult, ImageResult, EngineConfig

Jun 8

restructure: move app.py to root, replace model submodules with HF Hub download script, add package markers

Jun 7

feat: scaffold repo structure with empty files and headers