{ "cells": [ { "cell_type": "code", "execution_count": 4, "id": "b304dfff", "metadata": { "scrolled": true }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Populating the interactive namespace from numpy and matplotlib\n" ] } ], "source": [ "%pylab inline" ] }, { "cell_type": "code", "execution_count": 5, "id": "f955e852", "metadata": {}, "outputs": [], "source": [ "import os\n", "os.environ[\"CUDA_VISIBLE_DEVICES\"] = \"1\"" ] }, { "cell_type": "code", "execution_count": 9, "id": "e9716000", "metadata": {}, "outputs": [], "source": [ "import time\n", "import os\n", "import tqdm\n", "import shutil\n", "import random\n", "import funcy\n", "import json\n", "import numpy as np\n", "import multiprocessing\n", "import pandas as pd\n", "from suno_utils.audio import Audio\n", "from suno_utils.audio.conversion import play_audio, get_audio_properties, get_duration_s\n", "from suno_utils.utils.slicer import get_vad_gaps, get_intervals_from_gaps\n", "\n", "\n", "DATE_DIR = \"2022_10_13\"\n", "\n", "BASE_DIR = \"/mnt/data-ssd-1/data/private/customer/ring_central/2022-10-13-poc/\"\n", "\n", "RAW_AUDIO_DIR = os.path.join(BASE_DIR, \"raw_audio\")\n", "TO_REV_DIR = os.path.join(BASE_DIR, \"to_rev\", DATE_DIR)\n", "TO_REV_AUDIO_DIR = os.path.join(TO_REV_DIR, \"audio\")\n", "REV_MANIFEST_FILEPATH = os.path.join(TO_REV_DIR, \"rev_manifest.jsonl\")\n", "FAILED_MANIFEST_FILEPATH = os.path.join(TO_REV_DIR, \"failed_manifest.jsonl\")\n", "FROM_REV_DIR = os.path.join(BASE_DIR, \"from_rev\", DATE_DIR)" ] }, { "cell_type": "code", "execution_count": 8, "id": "e22f6da7", "metadata": {}, "outputs": [], "source": [ "# shutil.rmtree(FROM_REV_DIR, ignore_errors=True)\n", "# shutil.rmtree(TO_REV_DIR, ignore_errors=True)\n", "# shutil.rmtree(TO_REV_AUDIO_DIR, ignore_errors=True)\n", "os.makedirs(FROM_REV_DIR, exist_ok=True)\n", "os.makedirs(TO_REV_DIR, exist_ok=True)\n", "os.makedirs(TO_REV_AUDIO_DIR, exist_ok=True)" ] }, { "cell_type": "code", "execution_count": 11, "id": "93a2b6e9", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "0 failed\n", "1426 files - 2.8 hours\n" ] } ], "source": [ "l1 = []\n", "e1 = []\n", "for fn in os.listdir(RAW_AUDIO_DIR):\n", " try:\n", " l1.append(get_duration_s(os.path.join(RAW_AUDIO_DIR, fn)))\n", " except:\n", " e1.append(fn) \n", "print(len(e1), \"failed\")\n", "print(len(l1), \"files -\", round(sum(l1) / 60 / 60, 1), \"hours\")" ] }, { "cell_type": "code", "execution_count": 6, "id": "7e83d447", "metadata": {}, "outputs": [], "source": [ "import portion\n", "from suno_utils.utils.numbers import safe_round\n", "from suno_utils.tasks.music import remove_music\n", " \n", "def prep_annotation_audio(audio, clean_audio=True):\n", " min_silence_gap = 0.05\n", " min_segment_dur_s = 3.0\n", " max_segment_dur_s = 10.0\n", " # TODO: remove background noise?\n", " if clean_audio:\n", " cleaned_audio = remove_music(audio, use_gpu=True)\n", " else:\n", " cleaned_audio = audio\n", " vad_gaps = get_vad_gaps(cleaned_audio, min_gap_s=min_silence_gap, vad_level=3, silent=True)\n", " silence_frac = np.sum([g.upper - g.lower for g in vad_gaps]) / audio.duration_s\n", "# print(\"{}% silence\".format(round(silence_frac * 100, 1)))\n", "\n", " # anything longer than a second should get excluded with pad\n", " max_silence_s = 1\n", " max_silence_pad = max_silence_s / 2\n", " excluded_intervals = portion.openclosed(0, 0)\n", " for vad_gap in vad_gaps:\n", " excluded_lower_s = safe_round(vad_gap.lower + max_silence_pad)\n", " excluded_upper_s = safe_round(vad_gap.upper - max_silence_pad)\n", " if excluded_upper_s - excluded_lower_s > 0:\n", " excluded_intervals |= portion.openclosed(excluded_lower_s, excluded_upper_s)\n", " \n", " speech_segments = get_intervals_from_gaps(\n", " vad_gaps,\n", " excluded_intervals=excluded_intervals,\n", " min_dur_s=min_segment_dur_s,\n", " max_dur_s=max_segment_dur_s,\n", " total_duration_s=audio.duration_s\n", " )\n", " tot_segment_duration_s = np.sum([end_s - start_s for start_s, end_s in speech_segments])\n", " cov_frac = tot_segment_duration_s / audio.duration_s\n", "# print(\"{}% segment coverage\".format(round(cov_frac * 100, 1)))\n", "# tot_segment_duration_mins = int(tot_segment_duration_s // 60)\n", "# tot_segment_duration_secs = int(np.ceil(tot_segment_duration_s % 60))\n", "# print(\"{}m {}s segment audio\".format(tot_segment_duration_mins, tot_segment_duration_secs))\n", "\n", " audios_rev = []\n", " segments_meta = []\n", " for n, (start_s, end_s) in enumerate(speech_segments):\n", "# indicator_str = \"a\" + str(n)\n", " indicator_str = str(n).zfill(2)\n", " audios_indicator = []\n", " for c in indicator_str:\n", " audios_indicator.append(Audio.from_file(f\"audio_indicators/{c}_fast.wav\"))\n", " audios_rev.extend(audios_indicator)\n", " segments_meta.append({\n", " \"segment_number\": n,\n", " \"type\": \"indicator\",\n", " \"duration_s\": safe_round(np.sum([a.duration_s for a in audios_indicator])),\n", " \"indicator_str\": indicator_str,\n", " })\n", " audios_rev.append(audio.get_slice(start_s, end_s))\n", " segments_meta.append({\n", " \"segment_number\": n,\n", " \"type\": \"speech\",\n", " \"duration_s\": safe_round(end_s - start_s),\n", " \"orginial_audio_offset_s\": start_s,\n", " })\n", " \n", " if len(audios_rev) == 0:\n", " return None, {\n", " \"tot_silence_frac\": round(silence_frac, 3),\n", " \"segment_cov_frac\": round(cov_frac, 3),\n", " }\n", "\n", " if (\n", " np.min([e[\"duration_s\"] for e in segments_meta if e[\"type\"] == \"speech\"]) < min_segment_dur_s or\n", " np.max([e[\"duration_s\"] for e in segments_meta if e[\"type\"] == \"speech\"]) > max_segment_dur_s\n", " ):\n", " raise ValueError(\"incorrect segment length detected\")\n", " \n", " audio_rev = Audio.concatenate(audios_rev)\n", " stitch_overhead_frac = (audio_rev.duration_s - tot_segment_duration_s) / audio_rev.duration_s\n", "# print(\"{}% stitching overhead\".format(round(stitch_overhead_frac * 100, 1)))\n", " submission_duration_s = np.ceil(audio_rev.duration_s / 60) * 60\n", " tot_overhead_frac = (submission_duration_s - tot_segment_duration_s) / submission_duration_s\n", "# print(\"{}% total overhead\".format(round(tot_overhead_frac * 100, 1)))\n", "\n", " submission_meta = {\n", " \"tot_silence_frac\": round(silence_frac, 3),\n", " \"segment_cov_frac\": round(cov_frac, 3),\n", " \"stitch_overhead_frac\": round(stitch_overhead_frac, 3),\n", " \"tot_overhead_frac\": round(tot_overhead_frac, 3),\n", " \"segments_meta\": segments_meta,\n", " }\n", " # TODO: alert on mostly silence\n", " # TODO: alert on total time too short \n", " # TODO: alert on coverage \n", " # TODO: alert stitching overhead\n", " # TODO: alert rev rounding overhead\n", " return audio_rev, submission_meta" ] }, { "cell_type": "code", "execution_count": null, "id": "c7f5de1e", "metadata": {}, "outputs": [], "source": [ "# filepath = filepaths[5]\n", "\n", "# audio = Audio.from_file(filepath, sample_rate=16_000, byte_width=2)\n", "# audio_rev, submission_meta = prep_annotation_audio(audio)\n", "# audio_rev.play()" ] }, { "cell_type": "code", "execution_count": 8, "id": "9b27da8b", "metadata": {}, "outputs": [], "source": [ "# !rm -rf /mnt/data-ssd-1/data/private/customer/sanas/2022-08-04-fili-callcenter/to_rev/*" ] }, { "cell_type": "code", "execution_count": 14, "id": "96d0f32a", "metadata": {}, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ " 65%|████████████████████████████████████████████████████████████████████████████████████████████▉ | 6898/10614 [38:44:13<17:47:49, 17.24s/it]IOPub message rate exceeded.\n", "The notebook server will temporarily stop sending output\n", "to the client in order to avoid crashing it.\n", "To change this limit, set the config variable\n", "`--NotebookApp.iopub_msg_rate_limit`.\n", "\n", "Current values:\n", "NotebookApp.iopub_msg_rate_limit=1000.0 (msgs/sec)\n", "NotebookApp.rate_limit_window=3.0 (secs)\n", "\n", "100%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 10614/10614 [59:10:39<00:00, 20.07s/it]\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "242/10614 files excluded\n" ] } ], "source": [ "import pandas as pd\n", "import tqdm\n", "import uuid\n", "\n", "def get_hotwords_from_filename(fname):\n", " fn = os.path.split(fname)[-1]\n", " fn = os.path.splitext(fn)[0]\n", " fn = \"_\".join(fn.split(\"_\")[:-1])\n", " fn = fn.replace(\" \", \"_\").replace(\"-\", \"_\").replace(\"__\", \"_\")\n", " fn = (\n", " fn.replace(\"_Male_\", \"_\")\n", " .replace(\"_Female_\", \"_\")\n", " .replace(\"Tagalog\", \"_\")\n", " .replace(\"_PH_\", \"_\")\n", " .strip(\"_\")\n", " )\n", " return fn.split(\"_\")\n", "\n", "metadata = []\n", "failed_metadata = []\n", "for n, filepath in tqdm.tqdm(enumerate(filepaths), total=len(filepaths)):\n", " \n", " try:\n", " audio = Audio.from_file(filepath, sample_rate=16_000, byte_width=2)\n", " audio_rev, submission_meta = prep_annotation_audio(audio)\n", " except:\n", " failed_metadata.append({\n", " \"original_audio_filepath\": filepath,\n", " })\n", " continue\n", " \n", " # make filter logic\n", " if audio_rev is None:\n", " failed_metadata.append({\n", " \"original_audio_filepath\": filepath,\n", " \"misc_meta\": {\n", " \"tot_silence_frac\": submission_meta[\"tot_silence_frac\"],\n", " \"segment_cov_frac\": submission_meta[\"segment_cov_frac\"],\n", " }\n", " })\n", " continue\n", " \n", " uid = str(uuid.uuid4())\n", " rev_filepath = os.path.join(TO_REV_AUDIO_DIR, uid + \".mp3\")\n", " audio_rev.to_mp3(rev_filepath)\n", " hotwords = []# get_hotwords_from_filename(filepath)\n", " \n", " rough_efficiency = submission_meta[\"tot_silence_frac\"] + submission_meta[\"segment_cov_frac\"]\n", " if rough_efficiency > 1.5 or rough_efficiency < 0.5:\n", " print(f\"weird coverage in {uid}\")\n", " \n", " metadata.append({\n", " \"uid\": uid,\n", " \"original_audio_filepath\": filepath,\n", " \"segments_meta\": submission_meta[\"segments_meta\"],\n", " \"audio_duration_s\": audio_rev.duration_s,\n", " \"audio_filepath\": rev_filepath,\n", " \"hotwords\": hotwords,\n", " \"misc_meta\": {\n", " \"tot_silence_frac\": submission_meta[\"tot_silence_frac\"],\n", " \"segment_cov_frac\": submission_meta[\"segment_cov_frac\"],\n", " \"stitch_overhead_frac\": submission_meta[\"stitch_overhead_frac\"],\n", " \"tot_overhead_frac\": submission_meta[\"tot_overhead_frac\"],\n", " }\n", " })\n", "\n", " if n % 100 == 0:\n", " with open(REV_MANIFEST_FILEPATH, \"w\") as f:\n", " for meta in metadata:\n", " f.write(json.dumps(meta) + \"\\n\")\n", " with open(FAILED_MANIFEST_FILEPATH, \"w\") as f:\n", " for meta in failed_metadata:\n", " f.write(json.dumps(meta) + \"\\n\")\n", " \n", "with open(REV_MANIFEST_FILEPATH, \"w\") as f:\n", " for meta in metadata:\n", " f.write(json.dumps(meta) + \"\\n\")\n", "with open(FAILED_MANIFEST_FILEPATH, \"w\") as f:\n", " for meta in failed_metadata:\n", " f.write(json.dumps(meta) + \"\\n\")\n", "print(\"{}/{} files excluded\".format(len(failed_metadata), len(failed_metadata) + len(metadata)))" ] }, { "cell_type": "code", "execution_count": 15, "id": "73860040", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "10372 files total\n", "1959.1h total\n", "482.0h rev total\n", "433.3h segment total\n" ] } ], "source": [ "tot_duration_s = [get_audio_properties(m[\"original_audio_filepath\"])[\"duration_s\"] for m in metadata]\n", "tot_rev_duration_s = [m[\"audio_duration_s\"] for m in metadata]\n", "tot_seg_duration_s = 0\n", "for m in metadata:\n", " for e in m[\"segments_meta\"]:\n", " if e[\"type\"] == \"speech\":\n", " tot_seg_duration_s += e[\"duration_s\"]\n", "print(len(metadata), \"files total\")\n", "print(\"{}h total\".format(round(sum(tot_duration_s) / 60 / 60, 1)))\n", "print(\"{}h rev total\".format(round(sum(tot_rev_duration_s) / 60 / 60, 1)))\n", "print(\"{}h segment total\".format(round(tot_seg_duration_s / 60 / 60, 1)))" ] }, { "cell_type": "code", "execution_count": null, "id": "e8faa9b6", "metadata": {}, "outputs": [], "source": [ "# !cat /mnt/data-ssd-1/data/private/customer/sanas/2022-08-04-fili-callcenter/to_rev/2022_08_11/rev_manifest.jsonl | wc -l" ] }, { "cell_type": "code", "execution_count": null, "id": "b36ebbe9", "metadata": {}, "outputs": [], "source": [ "# rough estimates\n", "# 3 days of prep-time\n", "# 2k hours total\n", "# 500 hours rev submission\n", "# 450 hours segments\n", "# 400 hours final segments" ] }, { "cell_type": "code", "execution_count": null, "id": "102c0781", "metadata": {}, "outputs": [], "source": [] }, { "cell_type": "code", "execution_count": null, "id": "588f5904", "metadata": {}, "outputs": [], "source": [] }, { "cell_type": "code", "execution_count": null, "id": "5172e5ef", "metadata": {}, "outputs": [], "source": [] }, { "cell_type": "markdown", "id": "149b3b8e", "metadata": {}, "source": [ "## (optional) Investigate for mistakes" ] }, { "cell_type": "code", "execution_count": 129, "id": "143da265", "metadata": {}, "outputs": [], "source": [ "metadata = []\n", "with open(REV_MANIFEST_FILEPATH) as f:\n", " for l in f.read().strip().split(\"\\n\"):\n", " metadata.append(json.loads(l))" ] }, { "cell_type": "code", "execution_count": 50, "id": "e6d1a1bc", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "found\n" ] } ], "source": [ "for meta in metadata:\n", " if meta[\"uid\"] == \"29c7be40-46ef-4000-a8e4-e0a4e4a6b828\":\n", " print(\"found\")\n", " break\n", "# print(meta[\"misc_meta\"][\"tot_silence_frac\"] + meta[\"misc_meta\"][\"segment_cov_frac\"])" ] }, { "cell_type": "code", "execution_count": null, "id": "e0489de1", "metadata": {}, "outputs": [], "source": [ "# 2 got cancelled\n", "# 29c7be40-46ef-4000-a8e4-e0a4e4a6b828 - \n", "# 48bdcb66-c070-42e4-9cec-7fa0652787e7 - 1 min of background chatter" ] }, { "cell_type": "code", "execution_count": 52, "id": "9fe48a0d", "metadata": {}, "outputs": [ { "data": { "text/html": [ "\n", "\n" ], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "play_audio(\"/mnt/data-ssd-1/data/private/customer/sanas/2022-08-04-fili-callcenter/to_rev/2022_08_07/audio/29c7be40-46ef-4000-a8e4-e0a4e4a6b828.mp3\")" ] }, { "cell_type": "code", "execution_count": null, "id": "1b79d2e8", "metadata": {}, "outputs": [], "source": [] }, { "cell_type": "code", "execution_count": null, "id": "1b3ca219", "metadata": {}, "outputs": [], "source": [] }, { "cell_type": "code", "execution_count": null, "id": "6c91afe9", "metadata": {}, "outputs": [], "source": [] }, { "cell_type": "markdown", "id": "0868d256", "metadata": {}, "source": [ "## (Optional) Check price" ] }, { "cell_type": "code", "execution_count": 44, "id": "37decb32", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "700 files total\n" ] }, { "data": { "text/plain": [ "suno 2334.3\n", "sanas 4715.9\n", "dtype: float64" ] }, "execution_count": 44, "metadata": {}, "output_type": "execute_result" } ], "source": [ "suno_price_per_hour = 72\n", "suno_price_per_min = suno_price_per_hour / 60\n", "\n", "sanas_price = 162 # dollars_per_hour\n", "sanas_price_per_s = sanas_price / 3600 # dollars per s\n", "\n", "\n", "costs = []\n", "for rm in metadata:\n", " sanas_duration_s = np.sum([sm[\"duration_s\"] for sm in rm[\"segments_meta\"] if sm[\"type\"] == \"speech\"])\n", " sanas_cost = sanas_price_per_s * sanas_duration_s\n", " \n", " suno_cost = np.ceil(rm[\"audio_duration_s\"] / 60.) * suno_price_per_min\n", " costs.append({\"suno\": suno_cost, \"sanas\": sanas_cost})\n", "\n", "print(len(metadata), \"files total\")\n", "costs = pd.DataFrame(costs)\n", "# suno 2770.8\n", "# sanas 4715.9\n", "costs.sum().round(1)" ] }, { "cell_type": "code", "execution_count": null, "id": "def684e9", "metadata": {}, "outputs": [], "source": [] }, { "cell_type": "code", "execution_count": null, "id": "fcf743da", "metadata": {}, "outputs": [], "source": [] }, { "cell_type": "code", "execution_count": null, "id": "7a31702b", "metadata": {}, "outputs": [], "source": [] }, { "cell_type": "markdown", "id": "88a9e9cc", "metadata": {}, "source": [ "## Send stuff to rev" ] }, { "cell_type": "code", "execution_count": 24, "id": "613bd82e", "metadata": {}, "outputs": [], "source": [ "ORDER_REF_STR = \"sns\"" ] }, { "cell_type": "code", "execution_count": 25, "id": "686b5db2", "metadata": {}, "outputs": [], "source": [ "metadata = []\n", "with open(REV_MANIFEST_FILEPATH) as f:\n", " for l in f.read().strip().split(\"\\n\"):\n", " metadata.append(json.loads(l))" ] }, { "cell_type": "code", "execution_count": 26, "id": "e282c309", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "32.4h total\n" ] } ], "source": [ "tot_duration_s = [m[\"audio_duration_s\"] for m in metadata]\n", "print(len(metadata), \"files total\")\n", "print(\"{}h total\".format(round(sum(tot_duration_s) / 60 / 60, 1)))" ] }, { "cell_type": "code", "execution_count": 37, "id": "81f46bd0", "metadata": {}, "outputs": [], "source": [ "# metadata[0]" ] }, { "cell_type": "markdown", "id": "b16a0dd0", "metadata": {}, "source": [ "### 01 - upload items" ] }, { "cell_type": "code", "execution_count": null, "id": "62b680f9", "metadata": {}, "outputs": [], "source": [] }, { "cell_type": "code", "execution_count": null, "id": "b99cfa4e", "metadata": {}, "outputs": [], "source": [] }, { "cell_type": "code", "execution_count": null, "id": "ce556216", "metadata": {}, "outputs": [], "source": [] }, { "cell_type": "code", "execution_count": null, "id": "302e99c8", "metadata": {}, "outputs": [], "source": [] }, { "cell_type": "markdown", "id": "5dac9a4c", "metadata": {}, "source": [ "## Playground" ] }, { "cell_type": "code", "execution_count": 22, "id": "bf2eecb1", "metadata": {}, "outputs": [], "source": [ "d = os.path.join(BASE_DIR, \"Continuum_GSDExtracts\")\n", "a = [os.path.join(d, fn) for fn in os.listdir(d)]" ] }, { "cell_type": "code", "execution_count": 23, "id": "dbc6cb5c", "metadata": {}, "outputs": [], "source": [ "d = os.path.join(BASE_DIR, \"Continuum-PH-ASR-1\")\n", "b = [os.path.join(d, fn) for fn in os.listdir(d)]" ] }, { "cell_type": "code", "execution_count": 36, "id": "806a7d38", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "" ] }, "execution_count": 36, "metadata": {}, "output_type": "execute_result" }, { "data": { "image/png": "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\n", "text/plain": [ "
" ] }, "metadata": { "needs_background": "light" }, "output_type": "display_data" } ], "source": [ "s1 = pd.Series([os.path.getsize(e) for e in a])\n", "s1.hist(bins=100)" ] }, { "cell_type": "code", "execution_count": 35, "id": "fe3e73ea", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "" ] }, "execution_count": 35, "metadata": {}, "output_type": "execute_result" }, { "data": { "image/png": "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\n", "text/plain": [ "
" ] }, "metadata": { "needs_background": "light" }, "output_type": "display_data" } ], "source": [ "s2 = pd.Series([os.path.getsize(e) for e in b])\n", "s2.hist(bins=100)" ] }, { "cell_type": "code", "execution_count": 38, "id": "9eb867c7", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "" ] }, "execution_count": 38, "metadata": {}, "output_type": "execute_result" }, { "data": { "image/png": "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\n", "text/plain": [ "
" ] }, "metadata": { "needs_background": "light" }, "output_type": "display_data" } ], "source": [ "pd.Series([\n", " get_audio_properties(e)[\"duration_s\"]\n", " for e in a\n", "]).hist(bins=100)" ] }, { "cell_type": "code", "execution_count": 37, "id": "97c36287", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "" ] }, "execution_count": 37, "metadata": {}, "output_type": "execute_result" }, { "data": { "image/png": "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\n", "text/plain": [ "
" ] }, "metadata": { "needs_background": "light" }, "output_type": "display_data" } ], "source": [ "pd.Series([\n", " get_audio_properties(e)[\"duration_s\"]\n", " for e in b\n", "]).hist(bins=100)" ] }, { "cell_type": "code", "execution_count": 44, "id": "ea68418a", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "" ] }, "execution_count": 44, "metadata": {}, "output_type": "execute_result" }, { "data": { "image/png": "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\n", "text/plain": [ "
" ] }, "metadata": { "needs_background": "light" }, "output_type": "display_data" } ], "source": [ "l1 = [\n", " (os.path.getsize(e), get_audio_properties(e)[\"duration_s\"]) \n", " for e in a\n", "]\n", "plt.scatter([e[0] for e in l1], [e[1] for e in l1])" ] }, { "cell_type": "code", "execution_count": 42, "id": "01a60b78", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "" ] }, "execution_count": 42, "metadata": {}, "output_type": "execute_result" }, { "data": { "image/png": "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\n", "text/plain": [ "
" ] }, "metadata": { "needs_background": "light" }, "output_type": "display_data" } ], "source": [ "l2 = [\n", " (os.path.getsize(e), get_audio_properties(e)[\"duration_s\"]) \n", " for e in b\n", "]\n", "plt.scatter([e[0] for e in l2], [e[1] for e in l2])" ] }, { "cell_type": "code", "execution_count": 45, "id": "646d7d4a", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "'/mnt/data-ssd-1/data/private/customer/sanas/2022-08-04-fili-callcenter/Continuum_GSDExtracts/2022061308183549909558765181264101.wav'" ] }, "execution_count": 45, "metadata": {}, "output_type": "execute_result" } ], "source": [ "a[0]" ] }, { "cell_type": "code", "execution_count": 46, "id": "fec704ec", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "'/mnt/data-ssd-1/data/private/customer/sanas/2022-08-04-fili-callcenter/Continuum-PH-ASR-1/JohnCedrick_Deri_Male_PH-Tagalog_1658860181906.wav'" ] }, "execution_count": 46, "metadata": {}, "output_type": "execute_result" } ], "source": [ "b[0]" ] }, { "cell_type": "code", "execution_count": 47, "id": "ee500d58", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "\r\n", "Input File : '/mnt/data-ssd-1/data/private/customer/sanas/2022-08-04-fili-callcenter/Continuum_GSDExtracts/2022061308183549909558765181264101.wav'\r\n", "Channels : 1\r\n", "Sample Rate : 8000\r\n", "Precision : 14-bit\r\n", "Duration : 00:23:25.49 = 11243920 samples ~ 105412 CDDA sectors\r\n", "File Size : 11.2M\r\n", "Bit Rate : 64.0k\r\n", "Sample Encoding: 8-bit u-law\r\n", "\r\n" ] } ], "source": [ "!soxi /mnt/data-ssd-1/data/private/customer/sanas/2022-08-04-fili-callcenter/Continuum_GSDExtracts/2022061308183549909558765181264101.wav" ] }, { "cell_type": "code", "execution_count": 48, "id": "6fb90311", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "\r\n", "Input File : '/mnt/data-ssd-1/data/private/customer/sanas/2022-08-04-fili-callcenter/Continuum-PH-ASR-1/JohnCedrick_Deri_Male_PH-Tagalog_1658860181906.wav'\r\n", "Channels : 1\r\n", "Sample Rate : 44100\r\n", "Precision : 16-bit\r\n", "Duration : 13:31:35.77 = 2147483625 samples = 3.65218e+06 CDDA sectors\r\n", "File Size : 159M\r\n", "Bit Rate : 26.1k\r\n", "Sample Encoding: 16-bit Signed Integer PCM\r\n", "\r\n" ] } ], "source": [ "!soxi /mnt/data-ssd-1/data/private/customer/sanas/2022-08-04-fili-callcenter/Continuum-PH-ASR-1/JohnCedrick_Deri_Male_PH-Tagalog_1658860181906.wav" ] }, { "cell_type": "code", "execution_count": null, "id": "985526ee", "metadata": {}, "outputs": [], "source": [ "Channels : 1\n", "Sample Rate : 8000\n", "Precision : 14-bit\n", "Duration : 00:23:25.49 = 11243920 samples ~ 105412 CDDA sectors\n", "File Size : 11.2M\n", "Bit Rate : 64.0k\n", "Sample Encoding: 8-bit u-law\n", " \n", "Channels : 1\n", "Sample Rate : 44100\n", "Precision : 16-bit\n", "Duration : 13:31:35.77 = 2147483625 samples = 3.65218e+06 CDDA sectors\n", "File Size : 159M\n", "Bit Rate : 26.1k\n", "Sample Encoding: 16-bit Signed Integer PCM" ] }, { "cell_type": "code", "execution_count": null, "id": "82925a7f", "metadata": {}, "outputs": [], "source": [] }, { "cell_type": "code", "execution_count": null, "id": "40d8029a", "metadata": {}, "outputs": [], "source": [] }, { "cell_type": "code", "execution_count": null, "id": "ed6af4ce", "metadata": {}, "outputs": [], "source": [] }, { "cell_type": "code", "execution_count": null, "id": "e0c52c3c", "metadata": {}, "outputs": [], "source": [] }, { "cell_type": "code", "execution_count": null, "id": "4bc8931d", "metadata": {}, "outputs": [], "source": [] } ], "metadata": { "kernelspec": { "display_name": "Python 3 (ipykernel)", "language": "python", "name": "python3" }, "language_info": { "codemirror_mode": { "name": "ipython", "version": 3 }, "file_extension": ".py", "mimetype": "text/x-python", "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", "version": "3.8.10" } }, "nbformat": 4, "nbformat_minor": 5 }