Commit History

Add voice chat feature with audio storage
4d777b5

nexusbert commited on

Install ffmpeg for torchcodec runtime support
0139faa

nexusbert commited on

Simplify audio post-processing; set pad token; add generation logging
110cbbd

nexusbert commited on

Fix smooth generation: add num_beams=5 for local languages, disable early_stopping, fix lang_norm variable, add generation logging
9868a45

nexusbert commited on

Fix audio fade-out: remove unnecessary interpolation when speed_factor=1.0, use scipy.signal.resample for better quality, improve normalization
2a6e73d

nexusbert commited on

Update main.py
6b0ef1a

nexusbert commited on

Fix warnings: add attention_mask support, set pad_token, use do_sample with temperature for /speak and /tts-stream
4af1727

nexusbert commited on

Merge branch 'space-push'
733e3ce

nexusbert commited on

Update main.py
6a81f9d

nexusbert commited on

Fix speak-ai: use _transcribe_impl helper to properly handle audio transcription flow
feae02a

nexusbert commited on

Add 0.8x playback speed to audio output
f15d801

nexusbert commited on

ASR lazy-load: per-repo cache under /tmp; writable caches; disable lifespan; Farmlingua branding
ead6187

nexusbert commited on

Reduce storage: move HF caches to /tmp; store model ckpt in /tmp/models; ASR snapshot_download to /tmp with no symlinks
b52b307

nexusbert commited on

Docker: remove ASR predownload; rely on runtime snapshot_download
934e4f4

nexusbert commited on

Uvicorn: disable lifespan to avoid CancelledError on startup in Spaces
34b0587

nexusbert commited on

ASR runtime fetch: use snapshot_download in _get_asr with HF_TOKEN; no Docker prefetch required
21e4340

nexusbert commited on

Rename to Farmlingua Speech System; enforce default voices; ignore speaker_name; update /tts-stream to defaults
73082a3

nexusbert commited on

ASR+Ask integration, single /speak, scipy WAV, build-time ASR cache, cleanup
af80a9d

nexusbert commited on

Fix: remove unreachable duplicate TTS block in /speak
9e73567

nexusbert commited on

Fix FileResponse background task; add StreamingResponse cleanup; add sounddevice and system libs
b2581bc

nexusbert commited on

TTS: use scipy.io.wavfile for WAV output; remove torchcodec dependency path
2dccd23

nexusbert commited on

TTS: robust ckpt handling; download to /tmp then move; make /code writable
055110d

nexusbert commited on

requirements: add torchcodec to enable torchaudio save backend
d8e7f14

nexusbert commited on

Dockerfile: avoid repo models/ dependency; skip large ckpt; install yarngpt if missing
9499fce

nexusbert commited on

Dockerfile: fix HF login RUN block; remove heredoc ; parsing issue
0d4f107

nexusbert commited on

Sync: add API, Dockerfile, assets (no large ckpt)
c0612a8

nexusbert commited on

Update Dockerfile
6271c90
verified

nexusbert commited on

Update main.py
56b42f8
verified

nexusbert commited on

Update app.py
62c3dde
verified

nexusbert commited on

Update Dockerfile
e81ecc4
verified

nexusbert commited on

initial commit
8cc7be2
verified

nexusbert commited on