speech-prep 0.1.3__py3-none-any.whl → 0.1.4__py3-none-any.whl

speech_prep/__init__.py

@@ -13,6 +13,7 @@ from .exceptions import (
     SilenceDetectionError,
     SpeechPrepError,
 )
+from .formats import AudioFormat
 
 # Import version from hatch-vcs
 try:
@@ -25,6 +26,7 @@ except ImportError:
 
 __all__ = [
     "SoundFile",
+    "AudioFormat",
     "SpeechPrepError",
     "FFmpegError",
     "FileValidationError",

speech_prep/core.py

@@ -6,6 +6,7 @@ from typing import Optional
 
 from .detection import calculate_median_silence, detect_silence
 from .exceptions import SpeechPrepError
+from .formats import AudioFormat
 from .processing import adjust_speed, convert_format, strip_silence
 from .utils import format_time, get_audio_properties
 
@@ -158,20 +159,24 @@ class SoundFile:
             return None
 
     def convert(
-        self, output_path: Path, audio_bitrate: Optional[str] = None
+        self,
+        output_path: Path,
+        target_format: AudioFormat,
+        audio_bitrate: Optional[str] = None,
     ) -> Optional["SoundFile"]:
         """
         Convert the audio file to a different format.
 
         Args:
             output_path: Path to save the converted file
+            target_format: Target audio format
             audio_bitrate: Optional bitrate for the output file (e.g., '192k', '320k')
 
         Returns:
             A new SoundFile instance for the converted file, or None if operation failed
         """
         try:
-            convert_format(self.path, output_path, audio_bitrate)
+            convert_format(self.path, output_path, target_format, audio_bitrate)
             return SoundFile(
                 output_path, self.noise_threshold_db, self.min_silence_duration
             )

speech_prep/formats.py

@@ -0,0 +1,15 @@
+"""Enums for audio file formats."""
+
+from enum import Enum
+
+
+class AudioFormat(Enum):
+    """Enum representing supported audio formats."""
+
+    MP3 = "mp3"
+    WAV = "wav"
+    FLAC = "flac"
+    AAC = "aac"
+    OGG = "ogg"
+    M4A = "m4a"
+    UNKNOWN = "unknown"

speech_prep/processing.py

@@ -5,6 +5,7 @@ import subprocess
 from typing import Optional
 
 from .exceptions import FFmpegError
+from .formats import AudioFormat
 
 
 def strip_silence(
@@ -67,7 +68,10 @@ def strip_silence(
 
 
 def convert_format(
-    input_path: Path, output_path: Path, audio_bitrate: Optional[str] = None
+    input_path: Path,
+    output_path: Path,
+    target_format: AudioFormat,
+    audio_bitrate: Optional[str] = None,
 ) -> None:
     """
     Convert the audio file to a different format.
@@ -75,6 +79,7 @@ def convert_format(
     Args:
         input_path: Path to the input audio file
         output_path: Path to save the converted file
+        target_format: Target audio format
         audio_bitrate: Optional bitrate for the output file (e.g., '192k', '320k')
 
     Raises:
@@ -90,9 +95,21 @@ def convert_format(
     # Add output file
     cmd.append(str(output_path))
 
-    input_format = input_path.suffix.lower().lstrip(".")
-    output_format = output_path.suffix.lower().lstrip(".")
-    print(f"Converting {input_path.name} from {input_format} to {output_format}")
+    # Determine the input format from the file extension
+    input_format = AudioFormat.UNKNOWN
+    try:
+        ext = input_path.suffix.lower().lstrip(".")
+        input_format = AudioFormat(ext)
+    except ValueError:
+        pass  # Keep as UNKNOWN if not found
+
+    # Use the provided target_format
+    output_format = target_format
+
+    print(
+        f"Converting {input_path.name} from "
+        f"{input_format.value} to {output_format.value}"
+    )
 
     _run_ffmpeg_command(cmd, "converting format")
 
@@ -136,10 +153,16 @@ def adjust_speed(input_path: Path, output_path: Path, speed_factor: float) -> No
     filter_str = ",".join(atempo_filters) if atempo_filters else "atempo=1.0"
 
     # Determine appropriate codec based on output format
-    output_format = output_path.suffix.lower()
-    if output_format == ".mp3":
+    output_format = AudioFormat.UNKNOWN
+    try:
+        ext = output_path.suffix.lower().lstrip(".")
+        output_format = AudioFormat(ext)
+    except ValueError:
+        pass  # Keep as UNKNOWN
+
+    if output_format == AudioFormat.MP3:
         codec = "libmp3lame"
-    elif output_format == ".wav":
+    elif output_format == AudioFormat.WAV:
         codec = "pcm_s16le"
     else:
         codec = "libmp3lame"  # Default to mp3 codec

speech_prep/utils.py

@@ -5,6 +5,7 @@ from pathlib import Path
 import subprocess
 
 from .exceptions import AudioPropertiesError, FileValidationError
+from .formats import AudioFormat
 
 
 def validate_file(file_path: Path) -> bool:
@@ -29,7 +30,7 @@ def validate_file(file_path: Path) -> bool:
     return True
 
 
-def get_audio_properties(file_path: Path) -> tuple[float, int, str]:
+def get_audio_properties(file_path: Path) -> tuple[float, int, AudioFormat]:
     """
     Extract audio properties (duration, file size, format) using ffprobe.
 
@@ -37,7 +38,8 @@ def get_audio_properties(file_path: Path) -> tuple[float, int, str]:
         file_path: Path to the audio file
 
     Returns:
-        Tuple of (duration, file_size, audio_format)
+        Tuple of (duration, file_size, audio_format) where audio_format
+        is an AudioFormat enum representing the detected audio format
 
     Raises:
         AudioPropertiesError: If properties cannot be extracted
@@ -71,10 +73,17 @@ def get_audio_properties(file_path: Path) -> tuple[float, int, str]:
         probe_data = json.loads(probe_result.stdout)["format"]
         duration = float(probe_data["duration"])
         file_size = int(probe_data["size"])
-        audio_format = probe_data["format_name"].split(",")[
+        format_str = probe_data["format_name"].split(",")[
             0
         ]  # Get the first format name
 
+        # Convert format string to enum
+        try:
+            audio_format = AudioFormat(format_str.lower())
+        except ValueError:
+            # If not a direct match, use UNKNOWN
+            audio_format = AudioFormat.UNKNOWN
+
         if duration <= 0 or file_size <= 0:
             raise AudioPropertiesError(
                 f"Invalid duration or file size for {file_path}. "

{speech_prep-0.1.3.dist-info → speech_prep-0.1.4.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: speech-prep
-Version: 0.1.3
+Version: 0.1.4
 Summary: Audio preprocessing toolkit for speech-to-text applications using ffmpeg
 Project-URL: Homepage, https://github.com/dimdasci/speech-prep
 Project-URL: Repository, https://github.com/dimdasci/speech-prep
@@ -60,21 +60,19 @@ uv sync  # or pip install -e .
 ## Quick Start
 
 ```python
-from speech_prep import SoundFile
+from speech_prep import SoundFile, AudioFormat
 from pathlib import Path
 
 # Load an audio file
 audio = SoundFile(Path("recording.wav"))
 
 if audio:
-    print(f"Duration: {audio.duration:.2f} seconds")
-    print(f"Format: {audio.format}")
-    print(f"Silence periods detected: {len(audio.silence_periods)}")
+    print(audio)  # Shows duration, format, file size, and silence periods
 
     # Clean up the audio for speech-to-text
     cleaned = audio.strip(output_path=Path("recording_stripped.wav"))
     faster = cleaned.speed(output_path=Path("recording_stripped_fast.wav"), speed_factor=1.2)
-    final = faster.convert(output_path=Path("clean.mp3"))
+    final = faster.convert(output_path=Path("clean.mp3", target_format=AudioFormat.MP3))
 
     print(f"Processed file saved: {final.path}")
 ```
@@ -84,7 +82,7 @@ if audio:
 ### Basic Operations
 
 ```python
-from speech_prep import SoundFile
+from speech_prep import SoundFile, AudioFormat
 from pathlib import Path
 
 # Load audio file
@@ -103,17 +101,18 @@ cleaned = audio.strip(output_path=Path("interview_leading.wav"), trailing=False)
 faster = audio.speed(output_path=Path("interview_fast.wav"), speed_factor=1.5)
 
 # Convert format
-mp3_file = audio.convert(output_path=Path("output.mp3"))
+mp3_file = audio.convert(output_path=Path("output.mp3"), target_format=AudioFormat.MP3)
 ```
 
 ### Processing Pipeline
 
 ```python
-from speech_prep import SoundFile
+from speech_prep import AudioFormat, SoundFile
 from pathlib import Path
 
 def prepare_for_transcription(input_file: Path, output_file: Path):
     """Prepare audio file for speech-to-text processing."""
+
     # Load the original file
     audio = SoundFile(input_file)
     if not audio:
@@ -121,7 +120,7 @@ def prepare_for_transcription(input_file: Path, output_file: Path):
     # Processing pipeline
     stripped = audio.strip(output_path=input_file.with_stem(input_file.stem + "_stripped"))
     faster = stripped.speed(output_path=input_file.with_stem(input_file.stem + "_stripped_fast"), speed_factor=1.1)
-    processed = faster.convert(output_path=output_file)
+    processed = faster.convert(output_path=output_file, target_format=AudioFormat.MP3)
     if processed:
         print(f"Original duration: {audio.duration:.2f}s")
         print(f"Processed duration: {processed.duration:.2f}s")
@@ -175,8 +174,10 @@ audio = SoundFile(
 cleaned = audio.strip(output_path=Path("custom_output.wav"))
 
 # Custom conversion settings
+from speech_prep import AudioFormat
 mp3 = audio.convert(
     output_path=Path("output.mp3"),
+    target_format=AudioFormat.MP3,
     audio_bitrate="192k"  # Custom bitrate
 )
 ```
@@ -193,16 +194,33 @@ SoundFile(file_path, noise_threshold_db=-30, min_silence_duration=0.5)
 #### Methods
 - **`strip(output_path, leading=True, trailing=True)`**: Remove silence
 - **`speed(output_path, speed_factor)`**: Adjust playback speed
-- **`convert(output_path, audio_bitrate=None)`**: Convert format
+- **`convert(output_path, target_format, audio_bitrate=None)`**: Convert format
 
 #### Properties
 - **`path`**: Path to the audio file
 - **`duration`**: Duration in seconds
-- **`format`**: Audio format
+- **`format`**: Audio format (AudioFormat enum)
 - **`file_size`**: File size in bytes
 - **`silence_periods`**: List of detected silence periods
 - **`median_silence`**: Median silence duration
 
+### AudioFormat Enum
+
+The `AudioFormat` enum represents supported audio formats:
+
+```python
+from speech_prep import AudioFormat
+
+# Available formats
+AudioFormat.MP3   # MP3 format
+AudioFormat.WAV   # WAV format
+AudioFormat.FLAC  # FLAC format
+AudioFormat.AAC   # AAC format
+AudioFormat.OGG   # OGG format
+AudioFormat.M4A   # M4A format
+AudioFormat.UNKNOWN  # Unknown/unsupported format
+```
+
 ## Contributing
 
 1. Fork the repository

speech_prep-0.1.4.dist-info/RECORD

@@ -0,0 +1,11 @@
+speech_prep/__init__.py,sha256=BWVsOFBywQYAiykMB3XJX6JQww155M6R8NLxNCn3Z10,891
+speech_prep/core.py,sha256=GCxmKlf_ovEiRRzM8vr3ucPjb1pWHrL-MzkfWAKtzgg,7715
+speech_prep/detection.py,sha256=D5_WkTYoFDUIYA2u6cfWK6E_Rd5R6g1Lng0Hh1UGgBs,3495
+speech_prep/exceptions.py,sha256=qZcIzM-IPltgJNtfmj5K4D8OJsL1zButmLnshas9m4M,1091
+speech_prep/formats.py,sha256=fYeOMpMOrl3LX62L32xoAo2qYgxl43UYbywX_4j2nbw,262
+speech_prep/processing.py,sha256=wFZEVt2nB4PSiRQu3thVBQnODe8DSdXVogo9b09L9q4,6231
+speech_prep/utils.py,sha256=vz5OWIHvICTa2sz3__rDFxLeDXi4j8B5hvT5vdFblMM,3949
+speech_prep-0.1.4.dist-info/METADATA,sha256=f1UUmZgGnH1TyFreBxi5XMGlSSMwQve9hzz4rAi13mY,7161
+speech_prep-0.1.4.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
+speech_prep-0.1.4.dist-info/licenses/LICENSE,sha256=-M8NcLlGaRvQqThXHq5g0D9CUR05KMhdswCB9s_0Sds,1066
+speech_prep-0.1.4.dist-info/RECORD,,

speech_prep-0.1.3.dist-info/RECORD

@@ -1,10 +0,0 @@
-speech_prep/__init__.py,sha256=0Eu8vjSjvG3sOQbN9dsjtQkKcVBPcLthK4Eit0UrtAQ,839
-speech_prep/core.py,sha256=pe4djUP1wQF4TJiaw1lg7xIvBzVHOMWP7dHgar3unt4,7567
-speech_prep/detection.py,sha256=D5_WkTYoFDUIYA2u6cfWK6E_Rd5R6g1Lng0Hh1UGgBs,3495
-speech_prep/exceptions.py,sha256=qZcIzM-IPltgJNtfmj5K4D8OJsL1zButmLnshas9m4M,1091
-speech_prep/processing.py,sha256=421IqfAcRUqMtXBsiTypSp_4H0X3uh5UjQ8Af-nPaX0,5684
-speech_prep/utils.py,sha256=_yjn1hoVVHfLc3nGAhD2n6bsevgweqNOt1rsDyahQnY,3585
-speech_prep-0.1.3.dist-info/METADATA,sha256=8wP2R43DbY7JH9S8r1_DJlWKPsYMgi9CIIl8HpZMLsI,6616
-speech_prep-0.1.3.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
-speech_prep-0.1.3.dist-info/licenses/LICENSE,sha256=-M8NcLlGaRvQqThXHq5g0D9CUR05KMhdswCB9s_0Sds,1066
-speech_prep-0.1.3.dist-info/RECORD,,