Initial commit

.gitignore

@@ -0,0 +1,169 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/#use-with-ide
+.pdm.toml
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/
+
+## By Reza
+.archive/
+samples/
+*_[0-9]
+*_[0-9][0-9]
+*_????-??-??
+*.zip
+

main.py

@@ -0,0 +1,39 @@
+import librosa
+import torch
+from transformers import Wav2Vec2ForCTC, Wav2Vec2Processor
+
+# MODEL = "m3hrdadfi/wav2vec2-large-xlsr-persian"
+MODEL = "/home/reza/data/huggingface-models/04.wav2vec2-large-xlsr-persian"
+
+
+def mp3_to_text(mp3_file_path):
+    # Load the MP3 file and resample to 16kHz
+    audio, sample_rate = librosa.load(mp3_file_path, sr=16000)
+    print()
+    print("Resampling is Done!")
+
+    # Load tokenizer and model from Hugging Face
+    tokenizer = Wav2Vec2Processor.from_pretrained(MODEL)
+    model = Wav2Vec2ForCTC.from_pretrained(MODEL)
+    print()
+    print("Loading model is Done!")
+
+    # Preprocess the audio
+    input_values = tokenizer(audio, sampling_rate=16000, return_tensors="pt", padding="longest").input_values
+    logits = model(input_values).logits
+    print()
+    print("Processing the audio is Done!")
+
+    # Decode the predicted IDs
+    predicted_ids = torch.argmax(logits, dim=-1)
+    transcription = tokenizer.batch_decode(predicted_ids)
+    print()
+    print("Decoding the prodicted IDs is Done!")
+
+    return transcription[0]
+
+# text = mp3_to_text("samples/captcha.mp3")
+text = mp3_to_text("samples/sample1.wav")
+print()
+print(text)
+

requirements.txt

@@ -0,0 +1,6 @@
+torch==2.1.1+cpu
+torchaudio==2.1.1+cpu
+transformers==4.35.2
+librosa==0.10.1
+
+--find-links https://download.pytorch.org/whl/cpu