{ "cells": [ { "cell_type": "markdown", "metadata": {}, "source": [ "# Long Audio ASR\n", "\n", "Let say you want to transcribe long audio using TorchAudio, malaya-speech able to do that." ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "
\n", "\n", "This tutorial is available as an IPython notebook at [malaya-speech/example/long-audio-asr-torchaudio](https://github.com/huseinzol05/malaya-speech/tree/master/example/long-audio-asr-torchaudio).\n", " \n", "
" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "
\n", "\n", "This module is not language independent, so it not save to use on different languages. Pretrained models trained on hyperlocal languages.\n", " \n", "
" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "
\n", "\n", "This is an application of malaya-speech Pipeline, read more about malaya-speech Pipeline at [malaya-speech/example/pipeline](https://github.com/huseinzol05/malaya-speech/tree/master/example/pipeline).\n", " \n", "
" ] }, { "cell_type": "code", "execution_count": 1, "metadata": {}, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ "`pyaudio` is not available, `malaya_speech.streaming.pyaudio` is not able to use.\n" ] } ], "source": [ "import malaya_speech\n", "from malaya_speech import Pipeline\n", "from malaya_speech.utils.astype import float_to_int" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "### Load VAD model\n", "\n", "We are going to use WebRTC VAD model, read more about VAD at https://malaya-speech.readthedocs.io/en/latest/load-vad.html" ] }, { "cell_type": "code", "execution_count": 2, "metadata": { "scrolled": true }, "outputs": [], "source": [ "vad_model = malaya_speech.vad.webrtc()" ] }, { "cell_type": "code", "execution_count": 3, "metadata": {}, "outputs": [ { "data": { "image/png": "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\n", "text/plain": [ "" ] }, "execution_count": 3, "metadata": {}, "output_type": "execute_result" } ], "source": [ "p_vad = Pipeline()\n", "pipeline = (\n", " p_vad.map(lambda x: float_to_int(x, divide_max_abs=False))\n", " .map(vad_model)\n", ")\n", "p_vad.visualize()" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Starting malaya-speech 1.4.0, streaming always returned a float32 array between -1 and +1 values." ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "### Streaming interface\n", "\n", "```python\n", "def stream(\n", " src,\n", " vad_model=None,\n", " asr_model=None,\n", " classification_model=None,\n", " format=None,\n", " option=None,\n", " buffer_size: int = 4096,\n", " sample_rate: int = 16000,\n", " segment_length: int = 2560,\n", " num_padding_frames: int = 20,\n", " ratio: float = 0.75,\n", " min_length: float = 0.1,\n", " max_length: float = 10.0,\n", " realtime_print: bool = True,\n", " **kwargs,\n", "):\n", " \"\"\"\n", " Stream an audio using torchaudio library.\n", "\n", " Parameters\n", " ----------\n", " vad_model: object, optional (default=None)\n", " vad model / pipeline.\n", " asr_model: object, optional (default=None)\n", " ASR model / pipeline, will transcribe each subsamples realtime.\n", " classification_model: object, optional (default=None)\n", " classification pipeline, will classify each subsamples realtime.\n", " format: str, optional (default=None)\n", " Supported `format` for `torchaudio.io.StreamReader`,\n", " https://pytorch.org/audio/stable/generated/torchaudio.io.StreamReader.html#torchaudio.io.StreamReader\n", " option: dict, optional (default=None)\n", " Supported `option` for `torchaudio.io.StreamReader`,\n", " https://pytorch.org/audio/stable/generated/torchaudio.io.StreamReader.html#torchaudio.io.StreamReader\n", " buffer_size: int, optional (default=4096)\n", " Supported `buffer_size` for `torchaudio.io.StreamReader`, buffer size in byte. Used only when src is file-like object,\n", " https://pytorch.org/audio/stable/generated/torchaudio.io.StreamReader.html#torchaudio.io.StreamReader\n", " sample_rate: int, optional (default = 16000)\n", " output sample rate.\n", " segment_length: int, optional (default=2560)\n", " usually derived from asr_model.segment_length * asr_model.hop_length,\n", " size of audio chunks, actual size in term of second is `segment_length` / `sample_rate`.\n", " num_padding_frames: int, optional (default=20)\n", " size of acceptable padding frames for queue.\n", " ratio: float, optional (default = 0.75)\n", " if 75% of the queue is positive, assumed it is a voice activity.\n", " min_length: float, optional (default=0.1)\n", " minimum length (second) to accept a subsample.\n", " max_length: float, optional (default=10.0)\n", " maximum length (second) to accept a subsample.\n", " realtime_print: bool, optional (default=True)\n", " Will print results for ASR.\n", " **kwargs: vector argument\n", " vector argument pass to malaya_speech.streaming.pyaudio.Audio interface.\n", "\n", " Returns\n", " -------\n", " result : List[dict]\n", " \"\"\"\n", "```" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "### Load ASR model" ] }, { "cell_type": "code", "execution_count": 4, "metadata": { "scrolled": true }, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
Size (MB)malay-malayamalay-fleur102Languagesinglish
mesolitica/conformer-tiny38.5{'WER': 0.17341180814, 'CER': 0.05957485024}{'WER': 0.19524478979, 'CER': 0.0830808938}[malay]NaN
mesolitica/conformer-base121{'WER': 0.122076123261, 'CER': 0.03879606324}{'WER': 0.1326737206665, 'CER': 0.05032914857}[malay]NaN
mesolitica/conformer-medium243{'WER': 0.12777757303, 'CER': 0.0393998776}{'WER': 0.1379928549, 'CER': 0.05876827088}[malay]NaN
mesolitica/emformer-base162{'WER': 0.175762423786, 'CER': 0.06233919000537}{'WER': 0.18303839134, 'CER': 0.0773853362}[malay]NaN
mesolitica/conformer-singlish121NaNNaN[singlish]{'WER': 0.08535878149, 'CER': 0.0452357273822,...
mesolitica/conformer-medium-mixed243{'WER': 0.122076123261, 'CER': 0.03879606324}{'WER': 0.1326737206665, 'CER': 0.05032914857}[malay, singlish]{'WER': 0.08535878149, 'CER': 0.0452357273822,...
\n", "
" ], "text/plain": [ " Size (MB) \\\n", "mesolitica/conformer-tiny 38.5 \n", "mesolitica/conformer-base 121 \n", "mesolitica/conformer-medium 243 \n", "mesolitica/emformer-base 162 \n", "mesolitica/conformer-singlish 121 \n", "mesolitica/conformer-medium-mixed 243 \n", "\n", " malay-malaya \\\n", "mesolitica/conformer-tiny {'WER': 0.17341180814, 'CER': 0.05957485024} \n", "mesolitica/conformer-base {'WER': 0.122076123261, 'CER': 0.03879606324} \n", "mesolitica/conformer-medium {'WER': 0.12777757303, 'CER': 0.0393998776} \n", "mesolitica/emformer-base {'WER': 0.175762423786, 'CER': 0.06233919000537} \n", "mesolitica/conformer-singlish NaN \n", "mesolitica/conformer-medium-mixed {'WER': 0.122076123261, 'CER': 0.03879606324} \n", "\n", " malay-fleur102 \\\n", "mesolitica/conformer-tiny {'WER': 0.19524478979, 'CER': 0.0830808938} \n", "mesolitica/conformer-base {'WER': 0.1326737206665, 'CER': 0.05032914857} \n", "mesolitica/conformer-medium {'WER': 0.1379928549, 'CER': 0.05876827088} \n", "mesolitica/emformer-base {'WER': 0.18303839134, 'CER': 0.0773853362} \n", "mesolitica/conformer-singlish NaN \n", "mesolitica/conformer-medium-mixed {'WER': 0.1326737206665, 'CER': 0.05032914857} \n", "\n", " Language \\\n", "mesolitica/conformer-tiny [malay] \n", "mesolitica/conformer-base [malay] \n", "mesolitica/conformer-medium [malay] \n", "mesolitica/emformer-base [malay] \n", "mesolitica/conformer-singlish [singlish] \n", "mesolitica/conformer-medium-mixed [malay, singlish] \n", "\n", " singlish \n", "mesolitica/conformer-tiny NaN \n", "mesolitica/conformer-base NaN \n", "mesolitica/conformer-medium NaN \n", "mesolitica/emformer-base NaN \n", "mesolitica/conformer-singlish {'WER': 0.08535878149, 'CER': 0.0452357273822,... \n", "mesolitica/conformer-medium-mixed {'WER': 0.08535878149, 'CER': 0.0452357273822,... " ] }, "execution_count": 4, "metadata": {}, "output_type": "execute_result" } ], "source": [ "malaya_speech.stt.transducer.available_pt_transformer()" ] }, { "cell_type": "code", "execution_count": 6, "metadata": { "scrolled": true }, "outputs": [], "source": [ "model = malaya_speech.stt.transducer.pt_transformer(model = 'mesolitica/conformer-base')" ] }, { "cell_type": "code", "execution_count": 7, "metadata": {}, "outputs": [], "source": [ "_ = model.eval()" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "### ASR Pipeline\n", "\n", "Feel free to add speech enhancement or any function, but in this example, I just keep it simple." ] }, { "cell_type": "code", "execution_count": 8, "metadata": {}, "outputs": [ { "data": { "image/png": "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\n", "text/plain": [ "" ] }, "execution_count": 8, "metadata": {}, "output_type": "execute_result" } ], "source": [ "p_asr = Pipeline()\n", "pipeline_asr = (\n", " p_asr.map(lambda x: model.beam_decoder([x])[0], name = 'speech-to-text')\n", ")\n", "p_asr.visualize()" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "**You need to make sure the last output should named as `speech-to-text` or else the streaming interface will throw an error**." ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "### Start streaming" ] }, { "cell_type": "code", "execution_count": 9, "metadata": { "scrolled": true }, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ "/home/husein/.local/lib/python3.8/site-packages/torchaudio/io/_stream_reader.py:696: UserWarning: The number of buffered frames exceeded the buffer size. Dropping the old frames. To avoid this, you can set a higher buffer_chunk_size value. (Triggered internally at /root/project/torchaudio/csrc/ffmpeg/stream_reader/buffer.cpp:157.)\n", " return self._be.process_packet(timeout, backoff)\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "luangkan waktu untuk ikutilah drama tikus ini apabila pangkat menjadi taruhan berapa jabatan pun bermula siapa antara mereka yang berjaya dan siapa pula yang tak ke mana mana dua kali sebagai amanah dalam dua kali episod lepas rashid jalan butuh yang berlubang kita tanya sebab aku banyak kebaikan dan pengetahuannya kita tua dia akan berlalu dengan sia sia tak boleh macam ni ini simple sangat kalau boleh aku nak nampak gempak depan datuk arif tak boleh buat macam ni masuk aku nak tanya ni kau buat apa ni kenapa simpan sangat simple sangat kan aku macam ni simple dapat ini kerja orang pemalas ambil kau aku nak kau aku nak proposal ni nampak gempak gempak bogel ada bas eh apa bendalah aku ada bas kau faham tak nak gempa macam mana lagi jangan nampak macam mana tempat lagi kau tanya aku itu kerja engkau tu kerja engkau aku pergi weh kau telefon lama lagi ke macam biasalah ni sebab apa pula dia kata pun pasal aku tak nampak simple sangat macam tujuh malas selama jah tu kau akulah macam tu siapa tu kena tukar dengan kau dulu kita orang satu beg tapi bezanya aku tak pandai kipas macam dia tu sama sekarang ni semua nak kipas tahu pun assalamualaikum tu asyik ada apa saya tahu pejabat kan ya betul saya dah tak sini sebab nak tolong datuk tolong apa ni saya sampai pagi macam ni mesti datuk tengah fikir nak pakai stokin apa dia kata apa kata mana tahu tak tahu nak pakai topi mana satu dengan kasut yang mana kita tahu satu atuk tak payahlah terkejut tak tahu nak tahu saya ni memang pakar kalau buat tolong orang bagus tak macam tu tahun ni saya tolong saya tak tahulah cakap apa awak ni betul betul ada kagum rashid banyak sudah tua saya akan tolong datuk buat keputusan tempat okey stokin warna kelabu ni kata kita sesuai dengan tu sebab warna kelabu mempengaruhimu seorang kalau dah tu nak tahu warna kelabu ni dikaitkan dengan kemerdekaan sesuai dengan stoking warna merah tu lampau benda tu saya rasa tak sesuai dengan perwatakan datuk sambutan lupa kalau awak saya macam macam pokemon ni sesuai ini melambangkan dia jatuh ni seorang yang ada tak sama okeylah " ] } ], "source": [ "samples = malaya_speech.streaming.torchaudio.stream('speech/podcast/2x5%20Ep%2010.wav',\n", " vad_model = p_vad, \n", " asr_model = p_asr,\n", " segment_length = 320)" ] }, { "cell_type": "code", "execution_count": 10, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "23" ] }, "execution_count": 10, "metadata": {}, "output_type": "execute_result" } ], "source": [ "len(samples)" ] }, { "cell_type": "code", "execution_count": 11, "metadata": {}, "outputs": [], "source": [ "import IPython.display as ipd\n", "import numpy as np" ] }, { "cell_type": "code", "execution_count": 18, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "{'wav_data': array([ 0.0458374 , 0.04632568, 0.0489502 , ..., -0.03302002,\n", " -0.03625488, -0.02584839], dtype=float32),\n", " 'timestamp': datetime.datetime(2023, 2, 17, 0, 31, 10, 914959),\n", " 'asr_model': 'tak boleh macam ni ini simple sangat kalau boleh aku nak nampak gempak depan datuk arif tak boleh buat macam ni masuk'}" ] }, "execution_count": 18, "metadata": {}, "output_type": "execute_result" } ], "source": [ "samples[4]" ] }, { "cell_type": "code", "execution_count": 19, "metadata": {}, "outputs": [ { "data": { "text/html": [ "\n", " \n", " " ], "text/plain": [ "" ] }, "execution_count": 19, "metadata": {}, "output_type": "execute_result" } ], "source": [ "ipd.Audio(samples[4]['wav_data'], rate = 16000)" ] } ], "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" }, "varInspector": { "cols": { "lenName": 16, "lenType": 16, "lenVar": 40 }, "kernels_config": { "python": { "delete_cmd_postfix": "", "delete_cmd_prefix": "del ", "library": "var_list.py", "varRefreshCmd": "print(var_dic_list())" }, "r": { "delete_cmd_postfix": ") ", "delete_cmd_prefix": "rm(", "library": "var_list.r", "varRefreshCmd": "cat(var_dic_list()) " } }, "types_to_exclude": [ "module", "function", "builtin_function_or_method", "instance", "_Feature" ], "window_display": false } }, "nbformat": 4, "nbformat_minor": 4 }