File size: 5,280 Bytes
9eb8ea2 ddf7f94 9eb8ea2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 | {
"nbformat": 4,
"nbformat_minor": 5,
"metadata": {
"colab": {
"provenance": [],
"gpuType": "T4"
},
"kernelspec": {
"name": "python3",
"display_name": "Python 3"
},
"language_info": {
"name": "python"
},
"accelerator": "GPU"
},
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# PakUrdu-Conversational-ASR \u2014 full-quality inference\n",
"\n",
"Run the **full r14 model** (merged adapter, fp16) on a **free GPU** \u2014 nothing installs on your machine.\n",
"\n",
"**Setup (one click):** enable a GPU accelerator before running:\n",
"- **Colab:** `Runtime \u2192 Change runtime type \u2192 T4 GPU`\n",
"- **Kaggle:** `Settings \u2192 Accelerator \u2192 GPU T4 x2` (or P100)\n",
"\n",
"Then upload an Urdu audio clip (wav/mp3/m4a\u2026) and run the cells top to bottom.\n",
"\n",
"More: [model card](https://huggingface.co/KhiredNetworks/PakUrdu-Conversational-ASR) \u00b7 ",
"[browser demo](https://huggingface.co/spaces/KhiredNetworks/PakUrdu-ASR-Demo) (runs on your device, no GPU needed) \u00b7 ",
"[proof notebook](https://www.kaggle.com/code/adeelejaz8611/e1-sr-proof-r14-sr133) (re-derives the certified 7.96% WER end-to-end)\n"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## 1 \u2014 Load the model (base + fine-tuned adapter, merged)\n",
"\n",
"Downloads ~1.6 GB once per session; takes a couple of minutes."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# One-time environment fix \u2014 some cloud images ship torchao 0.10, which peft's\n",
"# import check rejects. torchao is only needed for torchao-quantized adapters\n",
"# (not this one), so removing it is safe and instant.\n",
"%pip uninstall -y -q torchao\n",
"print(\"environment ok \u2014 continue below\")"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"import torch, torchaudio\n",
"from peft import PeftModel\n",
"from transformers import WhisperForConditionalGeneration, WhisperProcessor\n",
"\n",
"BASE = \"openai/whisper-large-v3-turbo\"\n",
"ADAPTER = \"KhiredNetworks/PakUrdu-Conversational-ASR\"\n",
"\n",
"processor = WhisperProcessor.from_pretrained(BASE)\n",
"model = WhisperForConditionalGeneration.from_pretrained(BASE, torch_dtype=torch.float16)\n",
"model = PeftModel.from_pretrained(model, ADAPTER).merge_and_unload().to(\"cuda\").eval()\n",
"print(\"model ready \u2014 full fp16 r14 (merged adapter)\")"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## 2 \u2014 Point it at your audio\n",
"\n",
"How to get your clip in:\n",
"- **Colab:** folder icon (left) \u2192 Upload, or run `from google.colab import files; files.upload()`\n",
"- **Kaggle:** `+ Add Input \u2192 Upload` (attach the clip as a dataset); the path looks like `/kaggle/input/<your-dataset>/clip.wav`\n",
"\n",
"Then set the path below."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"AUDIO_PATH = \"your_audio.wav\" # <- set this to your clip's path"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## 3 \u2014 Transcribe\n",
"Greedy decode, `language=ur` (the intended configuration). Clips longer than 30 s are\n",
"windowed (25 s windows, 1.5 s overlap) and stitched, so long audio works too."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"SR = 16000\n",
"\n",
"def merge_texts(parts):\n",
" # drop the duplicated overlap words at each window seam\n",
" out = []\n",
" for p in parts:\n",
" words = (p or \"\").strip().split()\n",
" drop = 0\n",
" for k in range(min(len(out), len(words), 12), 0, -1):\n",
" if out[len(out) - k:] == words[:k]:\n",
" drop = k\n",
" break\n",
" out.extend(words[drop:])\n",
" return \" \".join(out)\n",
"\n",
"@torch.no_grad()\n",
"def transcribe(path):\n",
" speech, sr = torchaudio.load(path) # (channels, samples)\n",
" speech = speech.mean(dim=0)\n",
" if sr != SR:\n",
" speech = torchaudio.functional.resample(speech, sr, SR)\n",
" texts, start, CHUNK, OVERLAP = [], 0, 25 * SR, int(1.5 * SR)\n",
" while start < len(speech):\n",
" end = min(start + CHUNK, len(speech))\n",
" feats = processor(speech[start:end].numpy(), sampling_rate=SR,\n",
" return_tensors=\"pt\").input_features.half().to(\"cuda\")\n",
" ids = model.generate(feats, language=\"ur\", task=\"transcribe\", do_sample=False)\n",
" texts.append(processor.batch_decode(ids, skip_special_tokens=True)[0].strip())\n",
" if end == len(speech):\n",
" break\n",
" start = end - OVERLAP\n",
" return merge_texts(texts)\n",
"\n",
"print(transcribe(AUDIO_PATH))"
]
}
]
} |