{ "_id": "6a5db6969baadeef8ab539ec", "Package": "whisper", "Title": "Native R 'torch' Implementation of 'OpenAI' 'Whisper'", "Version": "0.4.0", "Date": "2026-06-19", "Authors@R": "c(\nperson(\"Troy\", \"Hernandez\", role = c(\"aut\", \"cre\"),\nemail = \"troy@cornball.ai\",\ncomment = c(ORCID = \"0009-0005-4248-604X\")),\nperson(\"cornball.ai\", role = \"cph\"),\nperson(\"OpenAI\", role = \"cph\",\ncomment = \"Whisper model architecture and mel filterbank data (MIT license)\")\n)", "Description": "Speech-to-text transcription using a native R 'torch'\nimplementation of 'OpenAI' 'Whisper' model\n. Supports multiple model\nsizes from tiny (39M parameters) to large-v3 (1.5B parameters)\nwith integrated download from 'HuggingFace'\n via the 'hfhub' package. Provides\nautomatic speech recognition with optional language detection\nand translation to English. Audio preprocessing, mel\nspectrogram computation, and transformer-based encoder-decoder\ninference are all implemented in R using the 'torch' package.", "License": "MIT + file LICENSE", "Encoding": "UTF-8", "URL": "https://github.com/cornball-ai/whisper", "BugReports": "https://github.com/cornball-ai/whisper/issues", "Config/pak/sysreqs": "cmake make libavfilter-dev libuv1-dev libssl-dev", "Repository": "https://cornball-ai.r-universe.dev", "Date/Publication": "2026-06-20 01:39:00 UTC", "RemoteUrl": "https://github.com/cornball-ai/whisper", "RemoteRef": "HEAD", "RemoteSha": "880c4bb5410815c8dba04161987445b905973f4c", "NeedsCompilation": "no", "Packaged": { "Date": "2026-07-20 05:44:50 UTC", "User": "root" }, "Author": "Troy Hernandez [aut, cre] (ORCID:\n),\ncornball.ai [cph],\nOpenAI [cph] (Whisper model architecture and mel filterbank data (MIT\nlicense))", "Maintainer": "Troy Hernandez ", "_user": "cornball-ai", "_type": "src", "_file": "whisper_0.4.0.tar.gz", "_fileid": "https://r2.ropensci.org/d62fdf3b8ad1705f524255e260e3aac54acdb8946e5cc816a29d77d9a1c0d92c", "_filesize": 574627, "_sha256": "d62fdf3b8ad1705f524255e260e3aac54acdb8946e5cc816a29d77d9a1c0d92c", "_expires": "2026-10-28T05:48:04.000Z", "_created": "2026-07-20T05:44:50.000Z", "_published": "2026-07-20T05:48:06.203Z", "_jobs": [ { "job": 88280431312, "time": 144, "config": "linux-devel-x86_64", "r": "4.7.0", "check": "OK", "artifact": "8451975981" }, { "job": 88280431316, "time": 141, "config": "linux-release-x86_64", "r": "4.6.1", "check": "OK", "artifact": "8451975332" }, { "job": 88280431305, "time": 96, "config": "macos-oldrel-arm64", "r": "4.5.3", "check": "OK", "artifact": "8451980224" }, { "job": 88280431318, "time": 96, "config": "macos-release-arm64", "r": "4.6.1", "check": "OK", "artifact": "8451970043" }, { "job": 88280065976, "time": 179, "config": "source", "r": "4.6.1", "check": "OK", "artifact": "8451937236" }, { "job": 88280431313, "time": 125, "config": "wasm-release", "r": "4.6.0", "check": "OK", "artifact": "8451973110" }, { "job": 88280431321, "time": 77, "config": "windows-devel", "r": "4.7.0", "check": "OK", "artifact": "8451957518" }, { "job": 88280431320, "time": 85, "config": "windows-oldrel", "r": "4.5.3", "check": "OK", "artifact": "8451959886" }, { "job": 88280431325, "time": 87, "config": "windows-release", "r": "4.6.1", "check": "OK", "artifact": "8451960414" } ], "_host": "GitHub-Actions", "_buildurl": "https://github.com/r-universe/cornball-ai/actions/runs/29719720069", "_status": "success", "_upstream": "https://github.com/cornball-ai/whisper", "_commit": { "id": "880c4bb5410815c8dba04161987445b905973f4c", "author": "Troy Hernandez ", "committer": "GitHub ", "message": "Release whisper 0.4.0 (#24)\n\nBump 0.3.0.9 -> 0.4.0, consolidate NEWS, add Date. Code unchanged from #23.", "time": 1781919540 }, "_maintainer": { "name": "Troy Hernandez", "email": "troy@cornball.ai", "login": "troyhernandez", "description": "", "uuid": 5670773, "orcid": "0009-0005-4248-604X" }, "_distro": "resolute", "_registered": true, "_dependencies": [ { "package": "torch", "version": ">= 0.17.0", "role": "Imports" }, { "package": "av", "role": "Imports" }, { "package": "jsonlite", "role": "Imports" }, { "package": "hfhub", "role": "Imports" }, { "package": "safetensors", "role": "Imports" }, { "package": "stats", "role": "Imports" }, { "package": "utils", "role": "Imports" }, { "package": "tinytest", "role": "Suggests" } ], "_owner": "cornball-ai", "_selfowned": true, "_usedby": 0, "_updates": [ { "week": "2026-04", "n": 16 }, { "week": "2026-05", "n": 8 }, { "week": "2026-06", "n": 3 }, { "week": "2026-07", "n": 3 }, { "week": "2026-08", "n": 5 }, { "week": "2026-09", "n": 2 }, { "week": "2026-11", "n": 3 }, { "week": "2026-12", "n": 2 }, { "week": "2026-25", "n": 11 } ], "_tags": [], "_stars": 7, "_contributors": [ { "user": "troyhernandez", "count": 53, "uuid": 5670773 } ], "_userbio": { "uuid": 153995987, "type": "organization", "name": "cornball.ai", "followers": 17 }, "_downloads": { "count": 377, "source": "https://cranlogs.r-pkg.org/downloads/total/last-month/whisper" }, "_devurl": "https://github.com/cornball-ai/whisper", "_searchresults": 9, "_rbuild": "4.6.1", "_assets": [ "extra/citation.cff", "extra/citation.html", "extra/citation.json", "extra/citation.txt", "extra/contents.json", "extra/NEWS.html", "extra/NEWS.txt", "extra/readme.html", "extra/readme.md", "extra/whisper.html", "LICENSE", "manual.pdf" ], "_homeurl": "https://github.com/cornball-ai/whisper", "_realowner": "cornball-ai", "_cranurl": true, "_releases": [ { "version": "0.1.0", "date": "2026-02-06" }, { "version": "0.3.0", "date": "2026-03-13" }, { "version": "0.4.0", "date": "2026-06-20" } ], "_exports": [ "audio_to_mel", "detect_language", "download_whisper_model", "list_downloaded_models", "list_whisper_models", "load_audio", "load_whisper_model", "model_exists", "serve", "transcribe", "whisper_config", "whisper_device", "whisper_dtype", "whisper_pipeline", "whisper_tokenizer", "whisper_tune_gc" ], "_help": [ { "page": "dot-model_sizes", "title": "Model Download Utilities", "topics": [ ".model_sizes" ] }, { "page": "apply_bpe", "title": "Apply BPE Merges", "topics": [ "apply_bpe" ] }, { "page": "apply_timestamp_rules", "title": "Apply Timestamp Token Rules", "topics": [ "apply_timestamp_rules" ] }, { "page": "audio_duration", "title": "Get Audio Duration", "topics": [ "audio_duration" ] }, { "page": "audio_to_mel", "title": "Convert Audio to Mel Spectrogram", "topics": [ "audio_to_mel" ] }, { "page": "beam_search_decode", "title": "Beam Search Decode", "topics": [ "beam_search_decode" ] }, { "page": "build_byte_decoder", "title": "Build Reverse Byte Decoder", "topics": [ "build_byte_decoder" ] }, { "page": "byte_to_token", "title": "Convert Byte to BPE Token", "topics": [ "byte_to_token" ] }, { "page": "clean_text", "title": "Clean Transcribed Text", "topics": [ "clean_text" ] }, { "page": "compression_ratio", "title": "Compression Ratio", "topics": [ "compression_ratio" ] }, { "page": "compute_stft", "title": "Compute STFT Magnitude", "topics": [ "compute_stft" ] }, { "page": "compute_word_timestamps", "title": "Compute Word-Level Timestamps", "topics": [ "compute_word_timestamps" ] }, { "page": "copy_if_exists", "title": "Copy Weight if Exists", "topics": [ "copy_if_exists" ] }, { "page": "create_decoder", "title": "Create Decoder from Config", "topics": [ "create_decoder" ] }, { "page": "create_encoder", "title": "Create Encoder from Config", "topics": [ "create_encoder" ] }, { "page": "create_mel_filterbank_fallback", "title": "Create Mel Filterbank (Fallback)", "topics": [ "create_mel_filterbank_fallback" ] }, { "page": "decode_bpe_bytes", "title": "Decode BPE Bytes Back to Text", "topics": [ "decode_bpe_bytes" ] }, { "page": "decode_timestamp", "title": "Decode Timestamp Token", "topics": [ "decode_timestamp" ] }, { "page": "decode_with_fallback", "title": "Decode with Temperature Fallback", "topics": [ "decode_with_fallback" ] }, { "page": "detect_language", "title": "Detect Language", "topics": [ "detect_language" ] }, { "page": "detect_language_from_mel", "title": "Detect Language from Mel Spectrogram", "topics": [ "detect_language_from_mel" ] }, { "page": "detect_language_from_pipeline", "title": "Detect Language from Pipeline", "topics": [ "detect_language_from_pipeline" ] }, { "page": "download_tokenizer_files", "title": "Download Tokenizer Files from HuggingFace", "topics": [ "download_tokenizer_files" ] }, { "page": "download_whisper_model", "title": "Download Model from HuggingFace", "topics": [ "download_whisper_model" ] }, { "page": "dtw_align", "title": "DTW Alignment", "topics": [ "dtw_align" ] }, { "page": "ensure_tokenizer_files", "title": "Ensure Tokenizer Files are Downloaded", "topics": [ "ensure_tokenizer_files" ] }, { "page": "expand_kv_cache", "title": "Expand KV Cache for Beam Search", "topics": [ "expand_kv_cache" ] }, { "page": "extract_segments", "title": "Extract Segments with Timestamps", "topics": [ "extract_segments" ] }, { "page": "forced_decode", "title": "Forced Decode", "topics": [ "forced_decode" ] }, { "page": "get_initial_tokens", "title": "Get Initial Decoder Tokens", "topics": [ "get_initial_tokens" ] }, { "page": "get_model_path", "title": "Get Model Cache Path", "topics": [ "get_model_path" ] }, { "page": "get_weights_path", "title": "Get Path to Model Weights", "topics": [ "get_weights_path" ] }, { "page": "greedy_decode", "title": "Greedy Decoding", "topics": [ "greedy_decode" ] }, { "page": "group_into_words", "title": "Group Subword Tokens into Words", "topics": [ "group_into_words" ] }, { "page": "hz_to_mel", "title": "Convert Hz to Mel Scale", "topics": [ "hz_to_mel" ] }, { "page": "is_timestamp_token", "title": "Check if Token is Timestamp", "topics": [ "is_timestamp_token" ] }, { "page": "list_downloaded_models", "title": "List Downloaded Models", "topics": [ "list_downloaded_models" ] }, { "page": "list_whisper_models", "title": "List Available Models", "topics": [ "list_whisper_models" ] }, { "page": "load_audio", "title": "Load and Preprocess Audio", "topics": [ "load_audio" ] }, { "page": "load_decoder_weights", "title": "Load Decoder Weights", "topics": [ "load_decoder_weights" ] }, { "page": "load_encoder_weights", "title": "Load Encoder Weights", "topics": [ "load_encoder_weights" ] }, { "page": "load_mel_filterbank", "title": "Load Pre-computed Mel Filterbank", "topics": [ "load_mel_filterbank" ] }, { "page": "load_whisper_model", "title": "Load Whisper Model", "topics": [ "load_whisper_model" ] }, { "page": "load_whisper_weights", "title": "Load Weights from Safetensors", "topics": [ "load_whisper_weights" ] }, { "page": "medfilt1", "title": "1D Median Filter", "topics": [ "medfilt1" ] }, { "page": "mel_to_hz", "title": "Convert Mel Scale to Hz", "topics": [ "mel_to_hz" ] }, { "page": "model_exists", "title": "Check if Model is Downloaded", "topics": [ "model_exists" ] }, { "page": "pad_or_trim", "title": "Pad or Trim Audio to Fixed Length", "topics": [ "pad_or_trim" ] }, { "page": "parse_device", "title": "Parse Device Argument", "topics": [ "parse_device" ] }, { "page": "parse_dtype", "title": "Parse Dtype Argument", "topics": [ "parse_dtype" ] }, { "page": "rearrange_kv_cache", "title": "Rearrange KV Cache by Beam Indices", "topics": [ "rearrange_kv_cache" ] }, { "page": "sample_decode", "title": "Sample Decode", "topics": [ "sample_decode" ] }, { "page": "serve", "title": "Serve whisper over HTTP", "topics": [ "serve" ] }, { "page": "split_audio", "title": "Split Long Audio into Chunks", "topics": [ "split_audio" ] }, { "page": "tokenizer_decode", "title": "Decode Token IDs to Text", "topics": [ "tokenizer_decode" ] }, { "page": "tokenizer_encode", "title": "Encode Text to Token IDs", "topics": [ "tokenizer_encode" ] }, { "page": "transcribe", "title": "Transcribe Audio", "topics": [ "transcribe" ] }, { "page": "transcribe_chunk", "title": "Transcribe Single Chunk", "topics": [ "transcribe_chunk" ] }, { "page": "transcribe_long", "title": "Transcribe Long Audio", "topics": [ "transcribe_long" ] }, { "page": "whisper_attention", "title": "Multi-Head Self-Attention", "topics": [ "whisper_attention" ] }, { "page": "whisper_config", "title": "Whisper Model Configurations", "topics": [ "whisper_config" ] }, { "page": "whisper_decoder", "title": "Text Decoder", "topics": [ "whisper_decoder" ] }, { "page": "whisper_decoder_layer", "title": "Decoder Layer", "topics": [ "whisper_decoder_layer" ] }, { "page": "whisper_device", "title": "Get Default Device", "topics": [ "whisper_device" ] }, { "page": "whisper_dtype", "title": "Get Default Dtype", "topics": [ "whisper_dtype" ] }, { "page": "whisper_encoder", "title": "Audio Encoder", "topics": [ "whisper_encoder" ] }, { "page": "whisper_encoder_layer", "title": "Encoder Layer", "topics": [ "whisper_encoder_layer" ] }, { "page": "whisper_lang_from_id", "title": "Get Language Code from Token ID", "topics": [ "whisper_lang_from_id" ] }, { "page": "whisper_lang_token", "title": "Get Language Token ID", "topics": [ "whisper_lang_token" ] }, { "page": "whisper_language_table", "title": "Whisper Language Table", "topics": [ "whisper_language_table" ] }, { "page": "whisper_model", "title": "Whisper Model Module", "topics": [ "whisper_model" ] }, { "page": "whisper_pipeline", "title": "Create a Whisper Pipeline", "topics": [ "whisper_pipeline" ] }, { "page": "WHISPER_SAMPLE_RATE", "title": "Whisper Audio Constants", "topics": [ "WHISPER_SAMPLE_RATE" ] }, { "page": "whisper_special_tokens", "title": "Special Token IDs", "topics": [ "whisper_special_tokens" ] }, { "page": "whisper_tokenizer", "title": "Create Whisper Tokenizer", "topics": [ "whisper_tokenizer" ] }, { "page": "whisper_tune_gc", "title": "Tune torch's CUDA garbage collection for whisper inference", "topics": [ "whisper_tune_gc" ] } ], "_readme": "https://github.com/cornball-ai/whisper/raw/HEAD/README.md", "_rundeps": [ "askpass", "av", "bit", "bit64", "callr", "cli", "coro", "curl", "desc", "farver", "filelock", "fs", "glue", "hfhub", "httr", "jsonlite", "labeling", "lifecycle", "magrittr", "mime", "openssl", "otel", "processx", "ps", "R6", "RColorBrewer", "Rcpp", "rlang", "safetensors", "scales", "sys", "torch", "triebeard", "urltools", "viridisLite", "withr" ], "_score": 4.498310553789601, "_indexed": true, "_nocasepkg": "whisper", "_universes": [ "cornball-ai", "troyhernandez" ], "_binaries": [ { "r": "4.7.0", "os": "linux", "version": "0.4.0", "date": "2026-07-20T05:47:06.000Z", "distro": "resolute", "commit": "880c4bb5410815c8dba04161987445b905973f4c", "fileid": "https://r2.ropensci.org/149b7231f1c172d2be4c708ba4f9c20c2757bb6b1a949d6f96f658020f36b3d4", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/cornball-ai/actions/runs/29719720069" }, { "r": "4.6.1", "os": "linux", "version": "0.4.0", "date": "2026-07-20T05:47:03.000Z", "distro": "resolute", "commit": "880c4bb5410815c8dba04161987445b905973f4c", "fileid": "https://r2.ropensci.org/2ee75302bbce7f69e0bf250c2f2a475fba1b3952629bf568593252b8dbab7e32", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/cornball-ai/actions/runs/29719720069" }, { "r": "4.5.3", "os": "mac", "version": "0.4.0", "date": "2026-07-20T05:47:27.000Z", "commit": "880c4bb5410815c8dba04161987445b905973f4c", "fileid": "https://r2.ropensci.org/ace86afb9c1f793e85caa7905ce0f7714ae2c30236c1da6fe6d62b7ad54d120e", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/cornball-ai/actions/runs/29719720069" }, { "r": "4.6.1", "os": "mac", "version": "0.4.0", "date": "2026-07-20T05:46:47.000Z", "commit": "880c4bb5410815c8dba04161987445b905973f4c", "fileid": "https://r2.ropensci.org/f3f89c5b6408ffc9e7ce5f7546dfa68c1edf38b8eb7f9d759271ca4328a9fe5f", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/cornball-ai/actions/runs/29719720069" }, { "r": "4.6.0", "os": "wasm", "version": "0.4.0", "date": "2026-07-20T05:47:19.000Z", "commit": "880c4bb5410815c8dba04161987445b905973f4c", "fileid": "https://r2.ropensci.org/4182a11caab6c7778d09a5e3b072a44e8d68c28599791789966aef63f09dc739", "status": "success", "buildurl": "https://github.com/r-universe/cornball-ai/actions/runs/29719720069" }, { "r": "4.7.0", "os": "win", "version": "0.4.0", "date": "2026-07-20T05:45:58.000Z", "commit": "880c4bb5410815c8dba04161987445b905973f4c", "fileid": "https://r2.ropensci.org/49bdd7a5452544f5e01b5fe59ccecfbe04d2d0218703a821923396e237d06573", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/cornball-ai/actions/runs/29719720069" }, { "r": "4.5.3", "os": "win", "version": "0.4.0", "date": "2026-07-20T05:45:59.000Z", "commit": "880c4bb5410815c8dba04161987445b905973f4c", "fileid": "https://r2.ropensci.org/38ba8c6231afa89031862724d506c79cf4d861825012b065fc347a361373ba7b", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/cornball-ai/actions/runs/29719720069" }, { "r": "4.6.1", "os": "win", "version": "0.4.0", "date": "2026-07-20T05:45:59.000Z", "commit": "880c4bb5410815c8dba04161987445b905973f4c", "fileid": "https://r2.ropensci.org/360927747d01595e6694ec79a5a258e6399da402dac5f5783ecda356ef42f9ac", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/cornball-ai/actions/runs/29719720069" } ] }