Init

.gitattributes

@@ -1,35 +1,6 @@
-*.7z filter=lfs diff=lfs merge=lfs -text
-*.arrow filter=lfs diff=lfs merge=lfs -text
-*.bin filter=lfs diff=lfs merge=lfs -text
-*.bz2 filter=lfs diff=lfs merge=lfs -text
-*.ckpt filter=lfs diff=lfs merge=lfs -text
-*.ftz filter=lfs diff=lfs merge=lfs -text
-*.gz filter=lfs diff=lfs merge=lfs -text
-*.h5 filter=lfs diff=lfs merge=lfs -text
-*.joblib filter=lfs diff=lfs merge=lfs -text
-*.lfs.* filter=lfs diff=lfs merge=lfs -text
-*.mlmodel filter=lfs diff=lfs merge=lfs -text
-*.model filter=lfs diff=lfs merge=lfs -text
-*.msgpack filter=lfs diff=lfs merge=lfs -text
-*.npy filter=lfs diff=lfs merge=lfs -text
-*.npz filter=lfs diff=lfs merge=lfs -text
-*.onnx filter=lfs diff=lfs merge=lfs -text
-*.ot filter=lfs diff=lfs merge=lfs -text
-*.parquet filter=lfs diff=lfs merge=lfs -text
-*.pb filter=lfs diff=lfs merge=lfs -text
-*.pickle filter=lfs diff=lfs merge=lfs -text
-*.pkl filter=lfs diff=lfs merge=lfs -text
-*.pt filter=lfs diff=lfs merge=lfs -text
-*.pth filter=lfs diff=lfs merge=lfs -text
-*.rar filter=lfs diff=lfs merge=lfs -text
-*.safetensors filter=lfs diff=lfs merge=lfs -text
-saved_model/**/* filter=lfs diff=lfs merge=lfs -text
-*.tar.* filter=lfs diff=lfs merge=lfs -text
-*.tar filter=lfs diff=lfs merge=lfs -text
-*.tflite filter=lfs diff=lfs merge=lfs -text
-*.tgz filter=lfs diff=lfs merge=lfs -text
-*.wasm filter=lfs diff=lfs merge=lfs -text
-*.xz filter=lfs diff=lfs merge=lfs -text
-*.zip filter=lfs diff=lfs merge=lfs -text
-*.zst filter=lfs diff=lfs merge=lfs -text
-*tfevents* filter=lfs diff=lfs merge=lfs -text
+sample_1.wav filter=lfs diff=lfs merge=lfs -text
+sample_2.wav filter=lfs diff=lfs merge=lfs -text
+sample_3.wav filter=lfs diff=lfs merge=lfs -text
+sample_4.wav filter=lfs diff=lfs merge=lfs -text
+sample_5.wav filter=lfs diff=lfs merge=lfs -text
+sample_6.wav filter=lfs diff=lfs merge=lfs -text

.gitignore

@@ -0,0 +1,5 @@
+.idea/
+.venv/
+.ruff_cache/
+
+flagged/

README.md

@@ -1,7 +1,7 @@
 ---
-title: St Hubert Uk Demo
-emoji: 🌍
-colorFrom: pink
+title: Streamlit: Speech-to-Text for Ukrainian (HuBERT)
+emoji: 🎙️
+colorFrom: blue
 colorTo: gray
 sdk: streamlit
 sdk_version: 1.37.1
@@ -10,4 +10,21 @@ pinned: false
 license: mit
 ---
 
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+## Install
+
+```shell
+uv venv --python 3.12
+
+source .venv/bin/activate
+
+uv pip install -r requirements.txt
+
+# in development mode
+uv pip install -r requirements-dev.txt
+```
+
+## Run
+
+```shell
+python app.py
+```

app.py

@@ -0,0 +1,243 @@
+import sys
+import time
+
+from importlib.metadata import version
+
+from os import remove
+from os.path import exists
+
+import numpy as np
+
+import torch
+import torchaudio
+import torchaudio.transforms as T
+
+import streamlit as st
+
+from streamlit.runtime.uploaded_file_manager import UploadedFile
+from transformers import HubertForCTC, Wav2Vec2Processor
+
+
+# Config
+model_name = "Yehor/hubert-uk"
+
+torchaudio_backend = "soundfile"
+
+min_duration = 0.5
+max_duration = 60
+
+concurrency_limit = 5
+use_torch_compile = False
+
+# Torch
+device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+torch_dtype = torch.float16 if torch.cuda.is_available() else torch.float32
+
+# Load the model
+asr_model = HubertForCTC.from_pretrained(
+    model_name, torch_dtype=torch_dtype, device_map=device
+)
+processor = Wav2Vec2Processor.from_pretrained(model_name)
+
+if use_torch_compile:
+    asr_model = torch.compile(asr_model)
+
+# Elements
+examples = [
+    "example_1.wav",
+    "example_2.wav",
+    "example_3.wav",
+    "example_4.wav",
+    "example_5.wav",
+    "example_6.wav",
+]
+
+examples_table = """
+| File  | Text |
+| ------------- | ------------- |
+| `example_1.wav`  | тема про яку не люблять говорити офіційні джерела у генштабі і міноборони це хімічна зброя окупанти вже тривалий час використовують хімічну зброю заборонену |
+| `example_2.wav`  | всіма конвенціями якщо спочатку це були гранати з дронів то тепер фіксують випадки застосування |
+| `example_3.wav`  | хімічних снарядів причому склад отруйної речовони різний а отже й наслідки для наших військових теж різні  |
+| `example_4.wav`  | використовує на фронті все що має і хімічна зброя не вийняток тож з чим маємо справу розбиралася марія моганисян |
+| `example_5.wav`  | двох тисяч випадків застосування росіянами боєприпасів споряджених небезпечними хімічними речовинами |
+| `example_6.wav`  | на всі писані норми марія моганисян олександр моторний спецкор марафон єдині новини |
+""".strip()
+
+authors_table = """
+## Authors
+
+Follow them in social networks and **contact** if you need any help or have any questions:
+
+| <img src="https://avatars.githubusercontent.com/u/7875085?v=4" width="100"> <br> **Yehor Smoliakov** |
+|------------------------------------------------------------------------------------------------------|
+| https://t.me/smlkw in Telegram                                                                       |
+| https://x.com/yehor_smoliakov at X                                                                   |
+| https://github.com/egorsmkv at GitHub                                                                |
+| https://huggingface.co/Yehor at Hugging Face                                                         |
+| or use [email protected]                                                                            |
+""".strip()
+
+description_head = f"""
+## Overview
+
+This space uses https://huggingface.co/Yehor/hubert-uk model to recognize audio files.
+
+> Due to resource limitations, audio duration **must not** exceed **{max_duration}** seconds.
+""".strip()
+
+description_foot = f"""
+## Community
+
+- **Discord**: https://discord.gg/yVAjkBgmt4
+- Speech Recognition: https://t.me/speech_recognition_uk
+- Speech Synthesis: https://t.me/speech_synthesis_uk
+
+## More
+
+Check out other ASR models: https://github.com/egorsmkv/speech-recognition-uk
+
+{authors_table}
+""".strip()
+
+transcription_value = """
+Recognized text will appear here.
+
+Choose **an example file** below the Recognize button, upload **your audio file**, or use **the microphone** to record own voice.
+""".strip()
+
+tech_env = f"""
+#### Environment
+
+- Python: {sys.version}
+- Torch device: {device}
+- Torch dtype: {torch_dtype}
+- Use torch.compile: {use_torch_compile}
+""".strip()
+
+tech_libraries = f"""
+#### Libraries
+
+- torch: {version('torch')}
+- torchaudio: {version('torchaudio')}
+- transformers: {version('transformers')}
+- accelerate: {version('accelerate')}
+- streamlit: {version('streamlit')}
+""".strip()
+
+
+# UploadedFile
+def inference(uploaded_file: UploadedFile):
+    audio_path = uploaded_file.file_id + '.wav'
+
+    with open(audio_path, 'wb') as f:
+        f.write(uploaded_file.getvalue())
+
+    if not audio_path:
+        st.error("Please upload an audio file.")
+        return
+
+    st.info("Starting recognition")
+
+    meta = torchaudio.info(audio_path, backend=torchaudio_backend)
+    duration = meta.num_frames / meta.sample_rate
+
+    if duration < min_duration:
+        st.error(
+            f"The duration of the file is less than {min_duration} seconds, it is {round(duration, 2)} seconds."
+        )
+        return
+    if duration > max_duration:
+        st.error(f"The duration of the file exceeds {max_duration} seconds.")
+        return
+
+    paths = [
+        audio_path,
+    ]
+
+    results = []
+
+    for path in paths:
+        t0 = time.time()
+
+        meta = torchaudio.info(audio_path, backend=torchaudio_backend)
+        audio_duration = meta.num_frames / meta.sample_rate
+
+        audio_input, sr = torchaudio.load(path, backend=torchaudio_backend)
+
+        if meta.num_channels > 1:
+            audio_input = torch.mean(audio_input, dim=0, keepdim=True)
+
+        if meta.sample_rate != 16_000:
+            resampler = T.Resample(sr, 16_000, dtype=audio_input.dtype)
+            audio_input = resampler(audio_input)
+
+        audio_input = audio_input.squeeze(0).numpy()
+
+        inputs = processor(
+            [audio_input], sampling_rate=16_000, padding=True
+        ).input_values
+        features = torch.tensor(np.array(inputs), dtype=torch_dtype).to(device)
+
+        with torch.inference_mode():
+            logits = asr_model(features).logits
+
+        predicted_ids = torch.argmax(logits, dim=-1)
+        predictions = processor.batch_decode(predicted_ids)
+
+        if not predictions:
+            predictions = "-"
+
+        elapsed_time = round(time.time() - t0, 2)
+        rtf = round(elapsed_time / audio_duration, 4)
+        audio_duration = round(audio_duration, 2)
+
+        results.append(
+            {
+                "path": path.split("/")[-1],
+                "transcription": "\n".join(predictions),
+                "audio_duration": audio_duration,
+                "rtf": rtf,
+            }
+        )
+
+    st.info("Finished!")
+
+    result_texts = []
+
+    for result in results:
+        result_texts.append(f'**{result["path"]}**')
+        result_texts.append("\n\n")
+        result_texts.append(f'> {result["transcription"]}')
+        result_texts.append("\n\n")
+        result_texts.append(f'**Audio duration**: {result["audio_duration"]}')
+        result_texts.append("\n")
+        result_texts.append(f'**Real-Time Factor**: {result["rtf"]}')
+
+    if exists(audio_path):
+        remove(audio_path)
+
+    return "\n".join(result_texts)
+
+
+st.title("Speech-to-Text for Ukrainian using HuBERT")
+st.markdown(description_head)
+
+st.markdown("## Usage")
+
+audio_file = st.file_uploader("Upload an audio file", type=["wav"])
+
+if st.button("Recognize"):
+    if audio_file is not None:
+        transcription = inference(audio_file)
+        st.markdown(transcription)
+    else:
+        st.error("Please upload an audio file.")
+
+st.markdown("### Examples")
+st.markdown(examples_table)
+
+st.markdown(description_foot, unsafe_allow_html=True)
+
+st.markdown("### Environment")
+st.markdown(tech_env)
+st.markdown(tech_libraries)

requirements-dev.txt

@@ -0,0 +1 @@
+ruff

requirements.txt

@@ -0,0 +1,11 @@
+streamlit
+
+torch
+torchaudio
+
+soundfile
+
+setuptools
+
+transformers
+accelerate

streamlit_config/config.toml

@@ -0,0 +1,290 @@
+[global]
+
+# By default, Streamlit displays a warning when a user sets both a widget
+# default value in the function defining the widget and a widget value via
+# the widget's key in `st.session_state`.
+
+# If you'd like to turn off this warning, set this to True.
+
+# Default: false
+# disableWidgetStateDuplicationWarning = false
+
+# If True, will show a warning when you run a Streamlit-enabled script
+# via "python my_script.py".
+
+# Default: true
+# showWarningOnDirectExecution = true
+
+
+[logger]
+
+# Level of logging: 'error', 'warning', 'info', or 'debug'.
+
+# Default: 'info'
+level = "error"
+
+# String format for logging messages. If logger.datetimeFormat is set,
+# logger messages will default to `%(asctime)s.%(msecs)03d %(message)s`. See
+# [Python's documentation](https://docs.python.org/2.6/library/logging.html#formatter-objects)
+# for available attributes.
+
+# Default: "%(asctime)s %(message)s"
+# messageFormat = "%(asctime)s %(message)s"
+
+
+[client]
+
+# Controls whether uncaught app exceptions and deprecation warnings
+# are displayed in the browser. By default, this is set to True and
+# Streamlit displays app exceptions and associated tracebacks, and
+# deprecation warnings, in the browser.
+
+# If set to False, deprecation warnings and full exception messages
+# will print to the console only. Exceptions will still display in the
+# browser with a generic error message. For now, the exception type and
+# traceback show in the browser also, but they will be removed in the
+# future.
+
+# Default: true
+# showErrorDetails = true
+
+# Change the visibility of items in the toolbar, options menu,
+# and settings dialog (top right of the app).
+
+# Allowed values:
+# * "auto" : Show the developer options if the app is accessed through
+# localhost or through Streamlit Community Cloud as a developer.
+# Hide them otherwise.
+# * "developer" : Show the developer options.
+# * "viewer" : Hide the developer options.
+# * "minimal" : Show only options set externally (e.g. through
+# Streamlit Community Cloud) or through st.set_page_config.
+# If there are no options left, hide the menu.
+
+# Default: "auto"
+# toolbarMode = "auto"
+
+# Controls whether to display the default sidebar page navigation in a
+# multi-page app. This only applies when app's pages are defined by the
+# `pages/` directory.
+
+# Default: true
+# showSidebarNavigation = true
+
+
+[runner]
+
+# Allows you to type a variable or string by itself in a single line of
+# Python code to write it to the app.
+
+# Default: true
+# magicEnabled = true
+
+# Handle script rerun requests immediately, rather than waiting for script
+# execution to reach a yield point. This makes Streamlit much more
+# responsive to user interaction, but it can lead to race conditions in
+# apps that mutate session_state data outside of explicit session_state
+# assignment statements.
+
+# Default: true
+fastReruns = false
+
+# Raise an exception after adding unserializable data to Session State.
+# Some execution environments may require serializing all data in Session
+# State, so it may be useful to detect incompatibility during development,
+# or when the execution environment will stop supporting it in the future.
+
+# Default: false
+# enforceSerializableSessionState = false
+
+# Adjust how certain 'options' widgets like radio, selectbox, and
+# multiselect coerce Enum members when the Enum class gets
+# re-defined during a script re-run.
+
+# Allowed values:
+# * "off": Disables Enum coercion.
+# * "nameOnly": Enum classes can be coerced if their member names match.
+# * "nameAndValue": Enum classes can be coerced if their member names AND
+# member values match.
+
+# Default: "nameOnly"
+# enumCoercion = "nameOnly"
+
+
+[server]
+
+# List of folders that should not be watched for changes.
+
+# Relative paths will be taken as relative to the current working directory.
+
+# Example: ['/home/user1/env', 'relative/path/to/folder']
+
+# Default: []
+# folderWatchBlacklist = []
+
+# Change the type of file watcher used by Streamlit, or turn it off
+# completely.
+
+# Allowed values:
+# * "auto" : Streamlit will attempt to use the watchdog module, and
+# falls back to polling if watchdog is not available.
+# * "watchdog" : Force Streamlit to use the watchdog module.
+# * "poll" : Force Streamlit to always use polling.
+# * "none" : Streamlit will not watch files.
+
+# Default: "auto"
+# fileWatcherType = "auto"
+
+# Symmetric key used to produce signed cookies. If deploying on multiple replicas, this should
+# be set to the same value across all replicas to ensure they all share the same secret.
+
+# Default: randomly generated secret key.
+# cookieSecret = "2efe79ee95dc08b35058032186268c9b1147069c04dc332bad9048e3284c6934"
+
+# If false, will attempt to open a browser window on start.
+
+# Default: false unless (1) we are on a Linux box where DISPLAY is unset, or
+# (2) we are running in the Streamlit Atom plugin.
+# headless = false
+
+# Automatically rerun script when the file is modified on disk.
+
+# Default: false
+# runOnSave = false
+
+# The address where the server will listen for client and browser
+# connections. Use this if you want to bind the server to a specific address.
+# If set, the server will only be accessible from this address, and not from
+# any aliases (like localhost).
+
+# Default: (unset)
+# address =
+
+# The port where the server will listen for browser connections.
+
+# Don't use port 3000 which is reserved for internal development.
+
+# Default: 8501
+# port = 8501
+
+# The base path for the URL where Streamlit should be served from.
+
+# Default: ""
+# baseUrlPath = ""
+
+# Enables support for Cross-Origin Resource Sharing (CORS) protection, for added security.
+
+# Due to conflicts between CORS and XSRF, if `server.enableXsrfProtection` is on and
+# `server.enableCORS` is off at the same time, we will prioritize `server.enableXsrfProtection`.
+
+# Default: true
+# enableCORS = true
+
+# Enables support for Cross-Site Request Forgery (XSRF) protection, for added security.
+
+# Due to conflicts between CORS and XSRF, if `server.enableXsrfProtection` is on and
+# `server.enableCORS` is off at the same time, we will prioritize `server.enableXsrfProtection`.
+
+# Default: true
+# enableXsrfProtection = true
+
+# Max size, in megabytes, for files uploaded with the file_uploader.
+
+# Default: 200
+# maxUploadSize = 200
+
+# Max size, in megabytes, of messages that can be sent via the WebSocket connection.
+
+# Default: 200
+# maxMessageSize = 200
+
+# Enables support for websocket compression.
+
+# Default: false
+# enableWebsocketCompression = false
+
+# Enable serving files from a `static` directory in the running app's directory.
+
+# Default: false
+# enableStaticServing = false
+
+# Server certificate file for connecting via HTTPS.
+# Must be set at the same time as "server.sslKeyFile".
+
+# ['DO NOT USE THIS OPTION IN A PRODUCTION ENVIRONMENT. It has not gone through security audits or performance tests. For the production environment, we recommend performing SSL termination by the load balancer or the reverse proxy.']
+# sslCertFile =
+
+# Cryptographic key file for connecting via HTTPS.
+# Must be set at the same time as "server.sslCertFile".
+
+# ['DO NOT USE THIS OPTION IN A PRODUCTION ENVIRONMENT. It has not gone through security audits or performance tests. For the production environment, we recommend performing SSL termination by the load balancer or the reverse proxy.']
+# sslKeyFile =
+
+
+[browser]
+
+# Internet address where users should point their browsers in order to
+# connect to the app. Can be IP address or DNS name and path.
+
+# This is used to:
+# - Set the correct URL for CORS and XSRF protection purposes.
+# - Show the URL on the terminal
+# - Open the browser
+
+# Default: "localhost"
+# serverAddress = "localhost"
+
+# Whether to send usage statistics to Streamlit.
+
+# Default: true
+# gatherUsageStats = true
+
+# Port where users should point their browsers in order to connect to the
+# app.
+
+# This is used to:
+# - Set the correct URL for XSRF protection purposes.
+# - Show the URL on the terminal (part of `streamlit run`).
+# - Open the browser automatically (part of `streamlit run`).
+
+# This option is for advanced use cases. To change the port of your app, use
+# `server.Port` instead. Don't use port 3000 which is reserved for internal
+# development.
+
+# Default: whatever value is set in server.port.
+# serverPort = 8501
+
+
+[mapbox]
+
+# Configure Streamlit to use a custom Mapbox
+# token for elements like st.pydeck_chart and st.map.
+# To get a token for yourself, create an account at
+# https://mapbox.com. It's free (for moderate usage levels)!
+
+# Default: ""
+# token = ""
+
+
+[theme]
+
+# The preset Streamlit theme that your custom theme inherits from.
+# One of "light" or "dark".
+# base =
+
+# Primary accent color for interactive elements.
+# primaryColor =
+
+# Background color for the main content area.
+# backgroundColor =
+
+# Background color used for the sidebar and most interactive widgets.
+# secondaryBackgroundColor =
+
+# Color used for almost all text.
+# textColor =
+
+# Font family for all text in the app, except code blocks. One of "sans serif",
+# "serif", or "monospace".
+# font =
+