update: add moore models for STT and TTS

Dockerfile

@@ -1,4 +1,5 @@
 FROM python:3.10-slim
+# FROM pytorch/pytorch:2.1.0-cuda11.8-cudnn8-runtime
 
 WORKDIR /app
 
@@ -8,4 +9,4 @@ COPY . .
 
 RUN pip install --no-cache-dir -r requirements.txt
 
-CMD ["uvicorn", "main:app", "--host", "0.0.0.0", "--port", "7860"]
+CMD ["uvicorn", "main:app", "--host", "0.0.0.0", "--port", "7860"]

language/mos_stt.py

@@ -1,9 +1,13 @@
 import base64, tempfile, os
 from transformers import pipeline
 import soundfile as sf
+# from huggingface_hub import login
 
 MODEL_NAME = "facebook/mms-1b-all"
 pipe = pipeline("automatic-speech-recognition", model=MODEL_NAME, model_kwargs={"target_lang": "mos"})
+# login(token=os.environ["HF_TOKEN"])
+# MODEL_NAME = "burkimbia/BIA-WHISPER-LARGE-SACHI_V3"
+# pipe = pipeline("automatic-speech-recognition", model=MODEL_NAME)
 
 
 def mooreSTT(audioBase64: str) -> dict:

requirements.txt

@@ -1,65 +1,156 @@
+absl-py==2.4.0
 aiohappyeyeballs==2.6.2
 aiohttp==3.14.1
 aiosignal==1.4.0
 annotated-doc==0.0.4
 annotated-types==0.7.0
+anyascii==0.3.3
 anyio==4.13.0
 async-timeout==5.0.1
 attrs==26.1.0
+audioread==3.1.0
 av==17.1.0
+babel==2.18.0
+bangla==0.0.6
+blinker==1.9.0
+blis==1.3.3
+bnnumerizer==0.0.2
+bnunicodenormalizer==0.1.7
+catalogue==2.0.10
 certifi==2026.5.20
 cffi==2.0.0
+charset-normalizer==3.4.7
 click==8.4.1
+cloudpathlib==0.24.0
 coloredlogs==15.0.1
+confection==1.3.3
+contourpy==1.2.1
+coqpit==0.0.17
 ctranslate2==4.8.0
+cycler==0.12.1
+cymem==2.0.13
+Cython==3.2.5
+dateparser==1.1.8
+decorator==5.3.1
+docopt==0.6.2
 edge-tts==7.2.8
+einops==0.8.2
+encodec==0.1.1
 exceptiongroup==1.3.1
 fastapi==0.136.3
 faster-whisper==1.2.1
 filelock==3.29.1
+Flask==3.1.3
 flatbuffers==25.12.19
+fonttools==4.63.0
 frozenlist==1.8.0
 fsspec==2026.4.0
+g2pkk==0.1.2
+grpcio==1.81.1
+gruut==2.2.3
+gruut-ipa==0.13.0
+gruut_lang_de==2.0.1
+gruut_lang_en==2.0.1
+gruut_lang_es==2.0.1
+gruut_lang_fr==2.0.2
 h11==0.16.0
-hf-xet==1.5.0
+hangul-romanize==0.1.0
+hf-xet==1.5.1
 httpcore==1.0.9
 httpx==0.28.1
-huggingface_hub==1.18.0
+huggingface_hub==1.19.0
 humanfriendly==10.0
 idna==3.18
+inflect==7.5.0
+itsdangerous==2.2.0
+jamo==0.4.1
+jieba==0.42.1
 Jinja2==3.1.6
+joblib==1.5.3
+jsonlines==1.2.0
+kiwisolver==1.5.0
+lazy-loader==0.5
+librosa==0.10.0
+llvmlite==0.47.0
+Markdown==3.10.2
 markdown-it-py==4.2.0
 MarkupSafe==3.0.3
+matplotlib==3.8.4
 mdurl==0.1.2
+more-itertools==11.1.0
 mpmath==1.3.0
+msgpack==1.2.0
 multidict==6.7.1
-networkx==3.4.2
-numpy==2.2.6
+murmurhash==1.0.15
+networkx==2.8.8
+nltk==3.9.4
+num2words==0.5.14
+numba==0.65.1
+numpy==1.22.0
 onnxruntime==1.23.2
 packaging==26.2
+pandas==1.5.3
+pillow==12.2.0
+platformdirs==4.10.0
+pooch==1.9.0
+preshed==3.0.13
 propcache==0.5.2
 protobuf==7.35.0
+psutil==7.2.2
 pycparser==3.0
 pydantic==2.13.4
 pydantic_core==2.46.4
 Pygments==2.20.0
+pynndescent==0.6.0
+pyparsing==3.3.2
+pypinyin==0.55.0
+pysbd==0.3.4
+python-crfsuite==0.9.12
+python-dateutil==2.9.0.post0
+pytz==2026.2
 PyYAML==6.0.3
 regex==2026.5.9
+requests==2.34.2
 rich==15.0.0
 safetensors==0.7.0
-scipy==1.15.3
+scikit-learn==1.7.2
+scipy==1.11.4
 sentencepiece==0.2.1
 shellingham==1.5.4
+six==1.17.0
+smart_open==7.6.1
 soundfile==0.14.0
+soxr==1.1.0
+spacy==3.8.14
+spacy-legacy==3.0.12
+spacy-loggers==1.0.5
+srsly==2.5.3
 starlette==1.2.1
+SudachiDict-core==20260428
+SudachiPy==0.6.11
 sympy==1.14.0
 tabulate==0.10.0
+tensorboard==2.20.0
+tensorboard-data-server==0.7.2
+thinc==8.3.13
+threadpoolctl==3.6.0
 tokenizers==0.22.2
 torch==2.12.0
+torchaudio==2.11.0
 tqdm==4.68.1
-transformers==5.10.2
+trainer==0.0.36
+transformers==5.12.1
+typeguard==4.5.2
 typer==0.25.1
 typing-inspection==0.4.2
 typing_extensions==4.15.0
+tzlocal==5.4
+umap-learn==0.5.7
+Unidecode==1.4.0
+urllib3==2.7.0
 uvicorn==0.49.0
+wasabi==1.1.3
+weasel==1.0.0
+Werkzeug==3.1.8
+wrapt==2.2.1
 yarl==1.24.2