mas-asr 0.1.0__tar.gz

mas_asr-0.1.0/PKG-INFO

@@ -0,0 +1,236 @@
+Metadata-Version: 2.3
+Name: mas-asr
+Version: 0.1.0
+Summary: Production-grade, modular multilingual ASR library with native script, mixed script, streaming, and fine-tuning support
+Author: ArYan9908
+Author-email: ArYan9908 <9908aryan@gmail.com>
+Requires-Dist: huggingface-hub>=0.23.0
+Requires-Dist: peft>=0.21.2
+Requires-Dist: sentencepiece>=0.2.2
+Requires-Dist: sounddevice>=0.5.6
+Requires-Dist: soundfile>=0.14.0
+Requires-Dist: torch>=2.14.1
+Requires-Dist: torchaudio>=2.11.0
+Requires-Dist: transformers>=5.19.0
+Requires-Dist: triton-windows>=3.8.0.post29
+Requires-Dist: peft>=0.10.0 ; extra == 'finetune'
+Requires-Dist: accelerate>=0.30.0 ; extra == 'finetune'
+Requires-Dist: datasets>=2.19.0 ; extra == 'finetune'
+Requires-Python: >=3.13
+Provides-Extra: finetune
+Description-Content-Type: text/markdown
+
+# mas-asr
+
+**mas-asr** is a production-grade, modular Python speech recognition library inspired by `openai-whisper` and `faster-whisper`. Built with first-class support for Indic languages, offering transcription in **native scripts**, **mixed scripts (Hinglish/code-mixing)**, and **romanized transliteration**, powered by models like **`bodhan-ai/indic-transcribe-flex`** (1.2B FastConformer + Transformer decoder).
+
+---
+
+## Key Features
+
+- **Whisper-like Intuitive API**: Load and transcribe with minimal code (`mas_asr.load_model(...)` & `model.transcribe(...)`).
+- **3 Output Script Modes**:
+  - `native`: Standard native script (Devanagari, Gurmukhi, Bengali, Tamil, etc.).
+  - `mixed`: Code-mixing & loanwords in Latin script with Indic digits (e.g., modern conversational messaging).
+  - `romanized`: Full phonetic transliteration in Latin script.
+- **27+ Indian Languages**: Hindi, Tamil, Telugu, Bengali, Kannada, Marathi, Malayalam, Punjabi, Gujarati, Odia, Urdu, Assamese, and more + English.
+- **Auto Long-Form Audio Segmentation**: Automatically splits audio exceeding 30 seconds at natural pauses using energy-based VAD to prevent context collapse.
+- **Real-Time Streaming**: VAD-buffered sliding window streaming processor for microphone input and WebSockets.
+- **Built-in CLI**: Transcribe directly from terminal with SRT, VTT, JSON, and TXT export.
+- **LoRA & PEFT Fine-Tuning**: Out-of-the-box support for low-rank adapter fine-tuning on domain-specific datasets.
+
+---
+
+## Installation
+
+Using `uv`:
+
+```bash
+uv add mas-asr
+```
+
+Or using standard `pip`:
+
+```bash
+pip install mas-asr
+```
+
+To install fine-tuning dependencies:
+
+```bash
+pip install "mas-asr[finetune]"
+```
+
+---
+
+## Quickstart (Python API)
+
+### Basic Transcription
+
+```python
+import mas_asr
+
+# Load model (auto-downloads from Hugging Face or loads local checkpoint directory)
+model = mas_asr.load_model("bodhan-ai/indic-transcribe-flex", device="cuda", compute_type="bfloat16")
+
+# Transcribe an audio file
+result = model.transcribe(
+    "speech.mp3",
+    language="hi",       # or None for automatic language detection
+    mode="native",       # "native", "mixed", or "romanized"
+    vad_filter=True,     # Auto-chunks long audio > 30s at natural pauses
+)
+
+print(result.text)
+print(f"Language: {result.language} (Confidence: {result.language_probability:.2f})")
+
+# Timestamped segments
+for seg in result.segments:
+    print(f"[{seg.start:.2f}s -> {seg.end:.2f}s] {seg.text}")
+```
+
+### High-Speed Inference with `torch.compile`
+
+Compile the model encoder to reduce kernel overhead and achieve faster transcription:
+
+```python
+# Enable torch.compile for reduced kernel launch overhead
+model = mas_asr.load_model(
+    "bodhan-ai/indic-transcribe-flex",
+    device="cuda",
+    compute_type="bfloat16",
+    compile=True,  # Compiles FastConformer encoder
+)
+```
+
+### Loading Trained LoRA Adapters
+
+```python
+# Load base model with a custom domain adapter attached
+model = mas_asr.load_model(
+    "bodhan-ai/indic-transcribe-flex",
+    adapter_path="./my_domain_adapters",
+)
+```
+
+### Multi-Mode Transcription in One Go
+
+```python
+# Transcribe into Native, Mixed, and Romanized scripts simultaneously
+outputs = model.all_modes("audio.wav", language="hi")
+print("Native:   ", outputs["native"])
+print("Mixed:    ", outputs["mixed"])
+print("Romanized:", outputs["romanized"])
+```
+
+### Export Subtitles (SRT / VTT)
+
+```python
+# Save SubRip Subtitles
+with open("subtitles.srt", "w", encoding="utf-8") as f:
+    f.write(result.to_srt())
+
+# Save WebVTT Subtitles
+with open("subtitles.vtt", "w", encoding="utf-8") as f:
+    f.write(result.to_vtt())
+```
+
+---
+
+## Real-Time Audio Streaming
+
+Use `AudioStreamer` for streaming microphone feeds, audio generator streams, or WebSockets:
+
+```python
+import mas_asr
+from mas_asr import AudioStreamer
+
+model = mas_asr.load_model("bodhan-ai/indic-transcribe-flex")
+streamer = AudioStreamer(model, language="hi", mode="native")
+
+# Feed 16kHz audio chunks (torch.Tensor, numpy array, or 16-bit PCM bytes)
+for pcm_chunk in audio_stream:
+    for event in streamer.feed(pcm_chunk):
+        if event.is_final:
+            print(f"\nFinal: {event.text}")
+        else:
+            print(f"Partial: {event.text}", end="\r")
+
+# Flush remaining audio when stream ends
+for event in streamer.flush():
+    print(f"\nFinal: {event.text}")
+```
+
+---
+
+## Command-Line Interface (CLI)
+
+```bash
+# Basic transcription
+mas-asr audio.wav --lang hi --mode native
+
+# Auto-detect language and show detection confidence
+mas-asr interview.mp3 --show-lang
+
+# Transcribe long audio and export to SRT subtitles
+mas-asr podcast.mp3 --output-format srt --output-dir ./subtitles/
+
+# Output all 3 modes (native, mixed, romanized)
+mas-asr clip.wav --all-modes
+
+# Batch process multiple audio files
+mas-asr ./recordings/*.wav --output-format json -o ./transcripts/
+```
+
+---
+
+## Fine-Tuning with LoRA / PEFT
+
+Adapt the 1.2B FastConformer model on domain-specific Indian language datasets with consumer GPUs:
+
+```python
+import mas_asr
+from mas_asr.finetune import get_canary_lora_model, ASREngineTrainer
+
+# Load base model
+base_model = mas_asr.load_model("bodhan-ai/indic-transcribe-flex")
+
+# Wrap with LoRA adapters
+lora_model = get_canary_lora_model(base_model.model, r=16, lora_alpha=32)
+
+# Train using ASREngineTrainer
+trainer = ASREngineTrainer(
+    model=lora_model,
+    fe=base_model.fe,
+    tokenizer=base_model.tokenizer,
+    train_dataset=my_hf_dataset,
+    batch_size=4,
+    learning_rate=1e-4,
+)
+
+trainer.train_epoch()
+trainer.save_adapters("./indic_lora_adapters")
+```
+
+See [examples/finetune_indic.py](file:///c:/Users/admin/Desktop/Projects/ITF/examples/finetune_indic.py) for a complete, runnable script.
+
+---
+
+## Supported Languages
+
+| Code | Language | Code | Language | Code | Language |
+|------|----------|------|----------|------|----------|
+| `as` | Assamese | `gu` | Gujarati | `mr` | Marathi  |
+| `bn` | Bengali  | `hi` | Hindi    | `ne` | Nepali   |
+| `bho`| Bhojpuri | `kn` | Kannada  | `or` | Odia     |
+| `doi`| Dogri    | `kok`| Konkani  | `pa` | Punjabi  |
+| `en` | English  | `ml` | Malayalam| `ta` | Tamil    |
+| `ur` | Urdu     | `mai`| Maithili | `te` | Telugu   |
+
+*(And additional scheduled regional languages: `bgc`, `bhb`, `brx`, `hne`, `ks`, `mni`, `sa`, `sat`, `sd`)*
+
+---
+
+## License
+
+Apache License 2.0.

mas_asr-0.1.0/README.md

@@ -0,0 +1,214 @@
+# mas-asr
+
+**mas-asr** is a production-grade, modular Python speech recognition library inspired by `openai-whisper` and `faster-whisper`. Built with first-class support for Indic languages, offering transcription in **native scripts**, **mixed scripts (Hinglish/code-mixing)**, and **romanized transliteration**, powered by models like **`bodhan-ai/indic-transcribe-flex`** (1.2B FastConformer + Transformer decoder).
+
+---
+
+## Key Features
+
+- **Whisper-like Intuitive API**: Load and transcribe with minimal code (`mas_asr.load_model(...)` & `model.transcribe(...)`).
+- **3 Output Script Modes**:
+  - `native`: Standard native script (Devanagari, Gurmukhi, Bengali, Tamil, etc.).
+  - `mixed`: Code-mixing & loanwords in Latin script with Indic digits (e.g., modern conversational messaging).
+  - `romanized`: Full phonetic transliteration in Latin script.
+- **27+ Indian Languages**: Hindi, Tamil, Telugu, Bengali, Kannada, Marathi, Malayalam, Punjabi, Gujarati, Odia, Urdu, Assamese, and more + English.
+- **Auto Long-Form Audio Segmentation**: Automatically splits audio exceeding 30 seconds at natural pauses using energy-based VAD to prevent context collapse.
+- **Real-Time Streaming**: VAD-buffered sliding window streaming processor for microphone input and WebSockets.
+- **Built-in CLI**: Transcribe directly from terminal with SRT, VTT, JSON, and TXT export.
+- **LoRA & PEFT Fine-Tuning**: Out-of-the-box support for low-rank adapter fine-tuning on domain-specific datasets.
+
+---
+
+## Installation
+
+Using `uv`:
+
+```bash
+uv add mas-asr
+```
+
+Or using standard `pip`:
+
+```bash
+pip install mas-asr
+```
+
+To install fine-tuning dependencies:
+
+```bash
+pip install "mas-asr[finetune]"
+```
+
+---
+
+## Quickstart (Python API)
+
+### Basic Transcription
+
+```python
+import mas_asr
+
+# Load model (auto-downloads from Hugging Face or loads local checkpoint directory)
+model = mas_asr.load_model("bodhan-ai/indic-transcribe-flex", device="cuda", compute_type="bfloat16")
+
+# Transcribe an audio file
+result = model.transcribe(
+    "speech.mp3",
+    language="hi",       # or None for automatic language detection
+    mode="native",       # "native", "mixed", or "romanized"
+    vad_filter=True,     # Auto-chunks long audio > 30s at natural pauses
+)
+
+print(result.text)
+print(f"Language: {result.language} (Confidence: {result.language_probability:.2f})")
+
+# Timestamped segments
+for seg in result.segments:
+    print(f"[{seg.start:.2f}s -> {seg.end:.2f}s] {seg.text}")
+```
+
+### High-Speed Inference with `torch.compile`
+
+Compile the model encoder to reduce kernel overhead and achieve faster transcription:
+
+```python
+# Enable torch.compile for reduced kernel launch overhead
+model = mas_asr.load_model(
+    "bodhan-ai/indic-transcribe-flex",
+    device="cuda",
+    compute_type="bfloat16",
+    compile=True,  # Compiles FastConformer encoder
+)
+```
+
+### Loading Trained LoRA Adapters
+
+```python
+# Load base model with a custom domain adapter attached
+model = mas_asr.load_model(
+    "bodhan-ai/indic-transcribe-flex",
+    adapter_path="./my_domain_adapters",
+)
+```
+
+### Multi-Mode Transcription in One Go
+
+```python
+# Transcribe into Native, Mixed, and Romanized scripts simultaneously
+outputs = model.all_modes("audio.wav", language="hi")
+print("Native:   ", outputs["native"])
+print("Mixed:    ", outputs["mixed"])
+print("Romanized:", outputs["romanized"])
+```
+
+### Export Subtitles (SRT / VTT)
+
+```python
+# Save SubRip Subtitles
+with open("subtitles.srt", "w", encoding="utf-8") as f:
+    f.write(result.to_srt())
+
+# Save WebVTT Subtitles
+with open("subtitles.vtt", "w", encoding="utf-8") as f:
+    f.write(result.to_vtt())
+```
+
+---
+
+## Real-Time Audio Streaming
+
+Use `AudioStreamer` for streaming microphone feeds, audio generator streams, or WebSockets:
+
+```python
+import mas_asr
+from mas_asr import AudioStreamer
+
+model = mas_asr.load_model("bodhan-ai/indic-transcribe-flex")
+streamer = AudioStreamer(model, language="hi", mode="native")
+
+# Feed 16kHz audio chunks (torch.Tensor, numpy array, or 16-bit PCM bytes)
+for pcm_chunk in audio_stream:
+    for event in streamer.feed(pcm_chunk):
+        if event.is_final:
+            print(f"\nFinal: {event.text}")
+        else:
+            print(f"Partial: {event.text}", end="\r")
+
+# Flush remaining audio when stream ends
+for event in streamer.flush():
+    print(f"\nFinal: {event.text}")
+```
+
+---
+
+## Command-Line Interface (CLI)
+
+```bash
+# Basic transcription
+mas-asr audio.wav --lang hi --mode native
+
+# Auto-detect language and show detection confidence
+mas-asr interview.mp3 --show-lang
+
+# Transcribe long audio and export to SRT subtitles
+mas-asr podcast.mp3 --output-format srt --output-dir ./subtitles/
+
+# Output all 3 modes (native, mixed, romanized)
+mas-asr clip.wav --all-modes
+
+# Batch process multiple audio files
+mas-asr ./recordings/*.wav --output-format json -o ./transcripts/
+```
+
+---
+
+## Fine-Tuning with LoRA / PEFT
+
+Adapt the 1.2B FastConformer model on domain-specific Indian language datasets with consumer GPUs:
+
+```python
+import mas_asr
+from mas_asr.finetune import get_canary_lora_model, ASREngineTrainer
+
+# Load base model
+base_model = mas_asr.load_model("bodhan-ai/indic-transcribe-flex")
+
+# Wrap with LoRA adapters
+lora_model = get_canary_lora_model(base_model.model, r=16, lora_alpha=32)
+
+# Train using ASREngineTrainer
+trainer = ASREngineTrainer(
+    model=lora_model,
+    fe=base_model.fe,
+    tokenizer=base_model.tokenizer,
+    train_dataset=my_hf_dataset,
+    batch_size=4,
+    learning_rate=1e-4,
+)
+
+trainer.train_epoch()
+trainer.save_adapters("./indic_lora_adapters")
+```
+
+See [examples/finetune_indic.py](file:///c:/Users/admin/Desktop/Projects/ITF/examples/finetune_indic.py) for a complete, runnable script.
+
+---
+
+## Supported Languages
+
+| Code | Language | Code | Language | Code | Language |
+|------|----------|------|----------|------|----------|
+| `as` | Assamese | `gu` | Gujarati | `mr` | Marathi  |
+| `bn` | Bengali  | `hi` | Hindi    | `ne` | Nepali   |
+| `bho`| Bhojpuri | `kn` | Kannada  | `or` | Odia     |
+| `doi`| Dogri    | `kok`| Konkani  | `pa` | Punjabi  |
+| `en` | English  | `ml` | Malayalam| `ta` | Tamil    |
+| `ur` | Urdu     | `mai`| Maithili | `te` | Telugu   |
+
+*(And additional scheduled regional languages: `bgc`, `bhb`, `brx`, `hne`, `ks`, `mni`, `sa`, `sat`, `sd`)*
+
+---
+
+## License
+
+Apache License 2.0.

mas_asr-0.1.0/pyproject.toml

@@ -0,0 +1,48 @@
+[project]
+name = "mas-asr"
+version = "0.1.0"
+description = "Production-grade, modular multilingual ASR library with native script, mixed script, streaming, and fine-tuning support"
+readme = "README.md"
+requires-python = ">=3.13"
+dependencies = [
+    "huggingface-hub>=0.23.0",
+    "peft>=0.21.2",
+    "sentencepiece>=0.2.2",
+    "sounddevice>=0.5.6",
+    "soundfile>=0.14.0",
+    "torch>=2.14.1",
+    "torchaudio>=2.11.0",
+    "transformers>=5.19.0",
+    "triton-windows>=3.8.0.post29",
+]
+
+[[project.authors]]
+name = "ArYan9908"
+email = "9908aryan@gmail.com"
+
+[project.optional-dependencies]
+finetune = [
+    "peft>=0.10.0",
+    "accelerate>=0.30.0",
+    "datasets>=2.19.0",
+]
+
+[project.scripts]
+mas-asr = "mas_asr.cli:main"
+
+[[tool.uv.index]]
+name = "pytorch-cu130"
+url = "https://download.pytorch.org/whl/cu130"
+explicit = true
+
+[[tool.uv.sources.torch]]
+index = "pytorch-cu130"
+marker = "sys_platform == 'linux' or sys_platform == 'win32'"
+
+[[tool.uv.sources.torchaudio]]
+index = "pytorch-cu130"
+marker = "sys_platform == 'linux' or sys_platform == 'win32'"
+
+[build-system]
+requires = ["uv_build>=0.12.21,<0.13.0"]
+build-backend = "uv_build"

mas_asr-0.1.0/pyproject.toml.orig

@@ -0,0 +1,47 @@
+[project]
+name = "mas-asr"
+version = "0.1.0"
+description = "Production-grade, modular multilingual ASR library with native script, mixed script, streaming, and fine-tuning support"
+readme = "README.md"
+authors = [
+    { name = "ArYan9908", email = "9908aryan@gmail.com" }
+]
+requires-python = ">=3.13"
+dependencies = [
+    "huggingface-hub>=0.23.0",
+    "peft>=0.21.2",
+    "sentencepiece>=0.2.2",
+    "sounddevice>=0.5.6",
+    "soundfile>=0.14.0",
+    "torch>=2.14.1",
+    "torchaudio>=2.11.0",
+    "transformers>=5.19.0",
+    "triton-windows>=3.8.0.post29",
+]
+
+[project.optional-dependencies]
+finetune = [
+    "peft>=0.10.0",
+    "accelerate>=0.30.0",
+    "datasets>=2.19.0",
+]
+
+[[tool.uv.index]]
+name = "pytorch-cu130"
+url = "https://download.pytorch.org/whl/cu130"
+explicit = true
+
+[tool.uv.sources]
+torch = [
+  { index = "pytorch-cu130", marker = "sys_platform == 'linux' or sys_platform == 'win32'" },
+]
+torchaudio = [
+  { index = "pytorch-cu130", marker = "sys_platform == 'linux' or sys_platform == 'win32'" },
+]
+
+[project.scripts]
+mas-asr = "mas_asr.cli:main"
+
+[build-system]
+requires = ["uv_build>=0.12.21,<0.13.0"]
+build-backend = "uv_build"

mas_asr-0.1.0/src/mas_asr/__init__.py

@@ -0,0 +1,29 @@
+"""mas-asr: Production-grade, modular multilingual ASR library with native and mixed script support."""
+
+from mas_asr.audio import get_audio_duration, load_audio, segment_audio
+from mas_asr.model import load_model, register_model_backend
+from mas_asr.models.indic_canary.lid import RECOMMENDED_LANGS, TRAINED_LANGS
+from mas_asr.models.indic_canary.model import MODES
+from mas_asr.streaming import AudioStreamer, StreamChunkEvent, stream_from_microphone
+from mas_asr.types import LanguageInfo, OutputMode, Segment, TranscriptionResult
+
+__version__ = "0.1.0"
+
+__all__ = [
+    "MODES",
+    "RECOMMENDED_LANGS",
+    "TRAINED_LANGS",
+    "AudioStreamer",
+    "LanguageInfo",
+    "OutputMode",
+    "Segment",
+    "StreamChunkEvent",
+    "TranscriptionResult",
+    "__version__",
+    "get_audio_duration",
+    "load_audio",
+    "load_model",
+    "register_model_backend",
+    "segment_audio",
+    "stream_from_microphone",
+]