ModelVérifiéExterne

Quran Stt Onnx

npl-1.1

Sourcehuggingface.co/Saboorhsn/quran-stt-onnx/tree/51ec9bcddeaf1c480bbe39064a2a3b88bc2ff224

TypeOtherVersionRevision 51ec9bcÉditeur@SaboorhsnCClasse

Source du modèle

Type: Other
Taille du fichier: 69,3 MB
Version: vRevision 51ec9bc
Mis à jour: 3 oct. 2026
Éditeur: @Saboorhsn
Téléchargements: 53
Source: Hugging Face

Description de la source

Zipformer-v3 Arabic / Quranic ASR & Forced Alignment

Attribution & Credits:
This model family is based on the state-of-the-art Zipformer2-CTC architecture developed by Quran-Lab (Quran-Lab/zipformer_p-arabic-v3). All original training, phonetization, and dataset curation credits belong to the Quran-Lab team and the authors of quran-transcript.

Quantization & Model Variants Table

This repository hosts ONNX quantized and precision-optimized variants designed for edge, CPU, and high-throughput GPU forced-alignment pipelines:

Model File	Precision / Quant	Size	Recommended Platform	Realtime Speedup (RTF)
`zipformer_p_arabic_v3.1.fp16.onnx`	Pure FP16 (Tensor Core)	126.2 MB	NVIDIA GPU (CUDA / Tensor Cores)	`>220x – 235x realtime` (RTF < 0.0045)
`zipformer_p_arabic_v3.1.onnx`	FP32 (v3.1 madd fine-tune)	250.8 MB	High-precision CPU / GPU	`~100x realtime` (GPU) / `3.5x` (CPU)
`zipformer_p_arabic_v3.1.int8.onnx`	INT8 / Q8 Quantized	69.3 MB	Mobile / Embedded / Laptop CPU	`~12x – 15x realtime` (x86 CPU)
`zipformer_p_arabic_v3.onnx`	FP32 (v3 Base)	250.8 MB	Reference FP32	`~100x realtime` (GPU)
`zipformer_p_arabic_v3.int8.onnx`	INT8 / Q8 (v3 Base)	69.3 MB	Standard CPU deployment	`~12x realtime` (CPU)
`tokens.txt`	CTC Symbol Table (251 units)	2.3 KB	Required for decoding	—
`config.json`	Model Hyperparameters	177 B	Config metadata	—

Benchmark Highlights (Surah Al-Kahf 18 & Surah Al-Baqarah 2)

Evaluated across continuous full-surah recitations on NVIDIA Tesla T4 GPU:

Parity: 0.00 ms mean delta against FP32 reference alignment.
Throughput: Aligns full 24.8-minute continuous audio (1,584 words) in 6.69 seconds flat.
Entire 30-Juz Quran (~25 hours audio): Full word-level forced-alignment and repeat-detection in ~6.3 minutes.

Usage with `quran-forced-align`

Install and align with zero configuration:

# Installs and runs with automatic GPU/CPU detection and auto-model caching:
pip install quran-forced-align

# Single Surah alignment (JSON + SRT):
quran-forced-align --surah 66 --audio audio/066_basit.mp3 --out output/066.json

Python Streaming ONNX Inference

import onnxruntime as ort
import numpy as np

# Load FP16 model on CUDA Execution Provider:
opts = ort.SessionOptions()
opts.graph_optimization_level = ort.GraphOptimizationLevel.ORT_ENABLE_ALL

session = ort.InferenceSession(
    "zipformer_p_arabic_v3.1.fp16.onnx",
    sess_options=opts,
    providers=[('CUDAExecutionProvider', {'device_id': 0, 'enable_cuda_graph': True}), 'CPUExecutionProvider']
)

Original Model Tree Files

Included in this repository are all symbol mappings and reference metadata from the original release:

tokens.txt: CTC 251-symbol table.
config.json: Model configuration.

License

Released under the Quran-Lab No-Profit License, Version 1.1 (NPL-1.1); free to use, study, adapt and redistribute for non-profit and educational purposes.

Sources

1 source

Hugging FacePrincipalVersion 51ec9bcddeaf1c480bbe39064a2a3b88bc2ff224

huggingface.co/Saboorhsn/quran-stt-onnx/tree/51ec9bcddeaf1c480bbe39064a2a3b88bc2ff224

Vérifié 3 oct.

Artefacts du modèle

1 artefact

quran-stt-int8.onnx

onnx · 69,3 MB · SHA-256 31755836528d…da6b · Hugging Face

Télécharger

Extraits de sources

3 extraits

Readme3 oct.huggingface.co/Saboorhsn/quran-stt-onnx

--- language: - ar tags: - speech - audio - automatic-speech-recognition - forced-alignment - quran - sherpa-onnx - zipformer - onnx license: other license_name: npl-1.1 license_link: https://huggingface.co/Quran-Lab/zipformer_p-arabic-v3/blob/main/LICENSE datasets: - Quran-Lab/quranic-asr-benchmark --- # Zipformer-v3 Arabic / Quranic ASR & Forced Alignment > **Attribution & Credits:** > This model family is based on the state-of-the-art **Zipformer2-CTC** architecture developed by **[Quran-Lab](https://huggingface.co/Quran-Lab)** ([Quran-Lab/zipformer_p-arabic-v3](https://huggingface.co/Quran-Lab/zipformer_p-arabic-v3)). All original training, phonetization, and dataset curation credits belong to the Quran-Lab team and the authors of [quran-transcript](https://github.com/obadx/quran-transcript). --- ## Quantization & Model Variants Table This repository hosts ONNX quantized and precision-optimized variants designed for **edge, CPU, and high-throughput GPU forced-alignment pipelines**: | Model File | Precision / Quant | Size | Recommended Platform | Realtime Speedup (RTF) | | :--- | :--- | :--- | :--- | :--- | | **`zipformer_p_arabic_v3.1.fp16.onnx`** | **Pure FP16 (Tensor Core)** | **126.2 MB** | **NVIDIA GPU (CUDA / Tensor Cores)** | **`>220x – 235x realtime` (RTF < 0.0045)** | | **`zipformer_p_arabic_v3.1.onnx`** | FP32 (v3.1 madd fine-tune) | 250.8 MB | High-precision CPU / GPU | `~100x realtime` (GPU) / `3.5x` (CPU) | | **`zipformer_p_arabic_v3.1.int8.onnx`** | INT8 / Q8 Quantized | 69.3 MB | Mobile / Embedded / Laptop CPU | `~12x – 15x realtime` (x86 CPU) | | **`zipformer_p_arabic_v3.onnx`** | FP32 (v3 Base) | 250.8 MB | Reference FP32 | `~100x realtime` (GPU) | | **`zipformer_p_arabic_v3.int8.onnx`** | INT8 / Q8 (v3 Base) | 69.3 MB | Standard CPU deployment | `~12x realtime` (CPU) | | **`tokens.txt`** | CTC Symbol Table (251 units) | 2.3 KB | **Required for decoding** | — | | **`config.json`** | Model Hyperparameters | 177 B | Config metadata | — | --- ## Benchmark Highlights (Surah Al-Kahf 18 & Surah Al-Baqarah 2) Evaluated across continuous full-surah recitations on NVIDIA Tesla T4 GPU: * **Parity:** **`0.00 ms` mean delta** against FP32 reference alignment. * **Throughput:** Aligns full 24.8-minute continuous audio (1,584 words) in **`6.69 seconds` flat**. * **Entire 30-Juz Quran (~25 hours audio):** Full word-level forced-alignment and...

Readme11 juil.huggingface.co/Saboorhsn/quran-stt-onnx

--- language: - ar license: apache-2.0 library_name: nemo tags: - audio - automatic-speech-recognition - arabic - quran - quranic-recitation - tajweed - fastconformer - mispronunciation-detection - onnx datasets: - tarteel-ai/everyayah - tarteel-ai/tlog metrics: - wer - cer base_model: - nvidia/stt_en_fastconformer_hybrid_large_pc - Muno459/fastconformer-quran pipeline_tag: automatic-speech-recognition --- # Quran STT — ONNX Exports ONNX-format exports of [Muno459/fastconformer-quran](https://huggingface.co/Muno459/fastconformer-quran) — a **FastConformer CTC** model for automatic speech recognition of Quranic recitation with Tajweed diacritics. Achieves **0.029% WER** on EveryAyah. ## How the Model Works ``` Audio (16 kHz mono) → Log-Mel Spectrogram [80 bands, 10 ms frames] → FastConformer Encoder (114.6M params, 8× temporal subsampling) → Linear Projection → LogSoftmax → [T_out × 1025] log-probs → CTC Greedy Decode (argmax + blank collapse) → token IDs ``` **Key details:** - **Encoder**: FastConformer Large — convolution-augmented Transformer. Each output frame covers 80 ms of audio. - **CTC Head**: Linear projection + LogSoftmax over 1025 classes (1024 SentencePiece BPE tokens + 1 blank). - **Decoder**: CTC greedy decoding — frame-independent, no language model, preserves mispronunciations. - **Tokenizer**: SentencePiece BPE, vocabulary size 1024, trained on Quranic Arabic with Tajweed diacritics. - **Fine-tuned** from NVIDIA's `stt_en_fastconformer_hybrid_large_pc` on EveryAyah + tlog. ## Files ### Unified Models | Path | Description | |------|-------------| | `onnx/model_fp32.onnx` | CTC-only ONNX, float32 (437 MB) | | `onnx/model_fp16.onnx` | CTC-only ONNX, float16 (219 MB) | | `onnx/model_int8.onnx` | CTC-only ONNX, int8 quantized (167 MB) | | `onnx/model_int8.ort` | CTC-only ORT format, optimized for runtime (175 MB) | | `onnx/model_quantized_int8.ort` | Unified Q8 model optimized for web-browser runtime (132 MB) | | `onnx/model_with_encoder.q8.ort` | Unified Q8 model with encoder outputs exposed (132 MB) | ### Split Streaming Models (Method 2b) | Path | Description | |------|-------------| | `onnx/fc_subsampler.ort` | Subsampler module of the split FastConformer Q8 model (1.6 MB) | | `onnx/fc_subsampler_fp32.ort` | Subsampler module of the split FastConformer model in FP32 precision (5.9 MB) | | `onnx/fc_context_encoder.ort` | Context...

Note17 juil.huggingface.co/Saboorhsn/quran-stt-onnx

Source context: 207 downloads · 1 likes · Pipeline automatic-speech-recognition · Library nemo · Repo Saboorhsn/quran-stt-onnx