HopeV1.0 / app.py

Commit History

5 days ago

  1. Claude: voice back to ritu; add SARVAM_TEMPERATURE (expressiveness) setting

    Sumedh
    d33ef6b
  2. Claude: change Sarvam voice to ishita

    Sumedh
    51e044b
  3. Claude: change Sarvam voice to roopa

    Sumedh
    1c52eaa
  4. Revert "Claude: LLM_MODEL switch + eval/llm_eval.py model comparison harness"⁠

    Sumedh
    cc6fbab
  5. Claude: LLM_MODEL switch + eval/llm_eval.py model comparison harness

    Sumedh
    b86fc81
  6. Claude: single TTS_ENGINE switch (sarvam/kokoro/browser); web UI now plays server TTS

    Sumedh
    315be98
  7. Claude: add Sarvam Bulbul (en-IN) TTS with Kokoro fallback and story audio cache

    Sumedh
    f073260

  1. Claude: make bot interactive + friendly + safe for kids⁠

    Sumedh
    59adc7c
  2. Claude: revert to working Kokoro checkpoint (af_bella, US English)⁠

    Sumedh
    b738a55
  3. Claude: switch Kokoro to Hindi female voice (hf_alpha) for Indian accent⁠

    Sumedh
    795c670
  4. Claude: revert TTS to Kokoro (af_bella) — restore kokoro-tts-checkpoint state⁠

    Sumedh
    8255c53
  5. Claude: speed up svara-tts via batched chunk generation + sdpa + token cap⁠

    Sumedh
    8e7b1dd
  6. Claude: replace indic-parler-tts with svara-tts (kenpath/svara-tts-v1)⁠

    Sumedh
    5fccb12
  7. Claude: chunk long text for indic-parler-tts to fix gibberish audio⁠

    Sumedh
    7dbf8f0
  8. Claude: fix indic-parler-tts description tokenizer loading + pin parler-tts to Dec 2024 commit⁠

    Sumedh
    22b006c
  9. Claude: replace Kokoro TTS with ai4bharat/indic-parler-tts for Indian female voice⁠

    Sumedh
    b0b9779

  1. Replace MeloTTS with Kokoro TTS (af_bella voice)⁠

    Sumedh +1: Claude Sonnet 4.6
    7d38e13
  2. Claude: use speed 0.68 for all classes (slowest, clearest for kids)

    Sumedh
    8e38352
  3. Claude: fix speaker ID EN-INDIA → EN_INDIA (underscore not hyphen)

    Sumedh
    d233faa
  4. Claude: replace sys.modules torchaudio hack with a real stub package in repo⁠

    Sumedh
    2b6532f
  5. Claude: fix torchaudio stub — set __spec__ so transformers importlib.find_spec does not crash⁠

    Sumedh
    838eb7f
  6. Claude: stub torchaudio with soundfile to fix libcudart.so.13 CUDA version mismatch⁠

    Sumedh
    c100816
  7. Claude: add torchaudio dep + fix melo_tts_to_wav returning None instead of empty string⁠

    Sumedh
    804166e
  8. Claude: enable show_error=True in Gradio launch for debugging

    Sumedh
    be357e9
  9. Claude: add MeloTTS Indian voice, onboarding personalization, class-based speed⁠

    Sumedh +1: Claude Sonnet 4.6
    4821868

  1. Adding Kokoro and fixing bug

    Sumedh
    62f462a

  1. Changed TTS to KOKORO

    Sumedh
    388734a
  2. Claude Update: Remove show_error

    Sumedh
    e3a35cc

  1. update

    Sumedh
    b0165e0

  1. updating api

    Sumedh
    68fddb7
  2. clearing some errors

    Sumedh
    a60b892
  3. gradio version

    Sumedh
    d22c3fd
  4. Updating for Whatsapp Integration

    Sumedh
    ef8e325

  1. Added Bathukamma story

    Verified signature
    3c5d60e

  1. Update app.py

    Verified signature
    ee37097
  2. hanging issue app update

    Verified signature
    4a7c40d

  1. fix for hagging issue

    Verified signature
    aad5368

  1. adding new stories

    Verified signature
    0150e39

  1. Update app.py

    Verified signature
    bf5d55d
  2. loading voice early

    Verified signature
    5e25b64
  3. Update app.py

    Verified signature
    df862c3
  4. Update app.py

    Verified signature
    0b2dfb5
  5. Update app.py

    Verified signature
    4408643
  6. Update app.py

    Verified signature
    d80e999
  7. Question slider update

    Verified signature
    6a48ceb

  1. adding piper-tts

    Peyyeti
    13a76b4

  1. revert

    Verified signature
    5d045f7
  2. Update app.py

    Verified signature
    3236635
  3. Update for Edge-TTS neerja Voice

    Verified signature
    8d98a6e

  1. adding greeting logic

    Verified signature
    057178f