listener: optimize transcription into 30s portions with timestamps

listener/.gitignore

@@ -25,3 +25,6 @@ rustc-ice-*.txt
 
 # Models dir
 models/
+
+# Transcription text file
+transcription.txt

listener/Cargo.lock

@@ -11,6 +11,21 @@ dependencies = [
  "memchr",
 ]
 
+[[package]]
+name = "android_system_properties"
+version = "0.1.5"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "819e7219dbd41043ac279b19830f2efc897156490d7fd6ea916720117ee66311"
+dependencies = [
+ "libc",
+]
+
+[[package]]
+name = "autocfg"
+version = "1.5.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "c08606f8c3cbf4ce6ec8e28fb0014a2c086708fe954eaa885384a6165172e7e8"
+
 [[package]]
 name = "bindgen"
 version = "0.72.1"
@@ -37,6 +52,21 @@ version = "2.11.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "c4512299f36f043ab09a583e57bceb5a5aab7a73db1805848e8fef3c9e8c78b3"
 
+[[package]]
+name = "block2"
+version = "0.6.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "cdeb9d870516001442e364c5220d3574d2da8dc765554b4a617230d33fa58ef5"
+dependencies = [
+ "objc2",
+]
+
+[[package]]
+name = "bumpalo"
+version = "3.20.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "5d20789868f4b01b2f2caec9f5c4e0213b41e3e5702a50157d699ae31ced2fcb"
+
 [[package]]
 name = "cc"
 version = "1.2.62"
@@ -62,6 +92,25 @@ version = "1.0.4"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "9330f8b2ff13f34540b44e946ef35111825727b38d33286ef986142615121801"
 
+[[package]]
+name = "cfg_aliases"
+version = "0.2.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "613afe47fcd5fac7ccf1db93babcb082c5994d996f20b8b159f2ad1658eb5724"
+
+[[package]]
+name = "chrono"
+version = "0.4.44"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "c673075a2e0e5f4a1dde27ce9dee1ea4558c7ffe648f576438a20ca1d2acc4b0"
+dependencies = [
+ "iana-time-zone",
+ "js-sys",
+ "num-traits",
+ "wasm-bindgen",
+ "windows-link",
+]
+
 [[package]]
 name = "clang-sys"
 version = "1.8.1"
@@ -82,6 +131,35 @@ dependencies = [
  "cc",
 ]
 
+[[package]]
+name = "core-foundation-sys"
+version = "0.8.7"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "773648b94d0e5d620f64f280777445740e61fe701025087ec8b57f45c791888b"
+
+[[package]]
+name = "ctrlc"
+version = "3.5.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "e0b1fab2ae45819af2d0731d60f2afe17227ebb1a1538a236da84c93e9a60162"
+dependencies = [
+ "dispatch2",
+ "nix",
+ "windows-sys",
+]
+
+[[package]]
+name = "dispatch2"
+version = "0.3.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "1e0e367e4e7da84520dedcac1901e4da967309406d1e51017ae1abfb97adbd38"
+dependencies = [
+ "bitflags",
+ "block2",
+ "libc",
+ "objc2",
+]
+
 [[package]]
 name = "either"
 version = "1.15.0"
@@ -100,12 +178,60 @@ version = "1.3.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "42703706b716c37f96a77aea830392ad231f44c9e9a67872fa5548707e11b11c"
 
+[[package]]
+name = "futures-core"
+version = "0.3.32"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "7e3450815272ef58cec6d564423f6e755e25379b217b0bc688e295ba24df6b1d"
+
+[[package]]
+name = "futures-task"
+version = "0.3.32"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "037711b3d59c33004d3856fbdc83b99d4ff37a24768fa1be9ce3538a1cde4393"
+
+[[package]]
+name = "futures-util"
+version = "0.3.32"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "389ca41296e6190b48053de0321d02a77f32f8a5d2461dd38762c0593805c6d6"
+dependencies = [
+ "futures-core",
+ "futures-task",
+ "pin-project-lite",
+ "slab",
+]
+
 [[package]]
 name = "glob"
 version = "0.3.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "0cc23270f6e1808e30a928bdc84dea0b9b4136a8bc82338574f23baf47bbd280"
 
+[[package]]
+name = "iana-time-zone"
+version = "0.1.65"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "e31bc9ad994ba00e440a8aa5c9ef0ec67d5cb5e5cb0cc7f8b744a35b389cc470"
+dependencies = [
+ "android_system_properties",
+ "core-foundation-sys",
+ "iana-time-zone-haiku",
+ "js-sys",
+ "log",
+ "wasm-bindgen",
+ "windows-core",
+]
+
+[[package]]
+name = "iana-time-zone-haiku"
+version = "0.1.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "f31827a206f56af32e590ba56d5d2d085f558508192593743f16b2306495269f"
+dependencies = [
+ "cc",
+]
+
 [[package]]
 name = "itertools"
 version = "0.13.0"
@@ -115,6 +241,18 @@ dependencies = [
  "either",
 ]
 
+[[package]]
+name = "js-sys"
+version = "0.3.98"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "67df7112613f8bfd9150013a0314e196f4800d3201ae742489d999db2f979f08"
+dependencies = [
+ "cfg-if",
+ "futures-util",
+ "once_cell",
+ "wasm-bindgen",
+]
+
 [[package]]
 name = "libc"
 version = "0.2.186"
@@ -149,6 +287,18 @@ version = "0.2.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "68354c5c6bd36d73ff3feceb05efa59b6acb7626617f4962be322a825e61f79a"
 
+[[package]]
+name = "nix"
+version = "0.31.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "5d6d0705320c1e6ba1d912b5e37cf18071b6c2e9b7fa8215a1e8a7651966f5d3"
+dependencies = [
+ "bitflags",
+ "cfg-if",
+ "cfg_aliases",
+ "libc",
+]
+
 [[package]]
 name = "nom"
 version = "7.1.3"
@@ -159,6 +309,42 @@ dependencies = [
  "minimal-lexical",
 ]
 
+[[package]]
+name = "num-traits"
+version = "0.2.19"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "071dfc062690e90b734c0b2273ce72ad0ffa95f0c74596bc250dcfd960262841"
+dependencies = [
+ "autocfg",
+]
+
+[[package]]
+name = "objc2"
+version = "0.6.4"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "3a12a8ed07aefc768292f076dc3ac8c48f3781c8f2d5851dd3d98950e8c5a89f"
+dependencies = [
+ "objc2-encode",
+]
+
+[[package]]
+name = "objc2-encode"
+version = "4.1.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "ef25abbcd74fb2609453eb695bd2f860d389e457f67dc17cafc8b8cbc89d0c33"
+
+[[package]]
+name = "once_cell"
+version = "1.21.4"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "9f7c3e4beb33f85d45ae3e3a1792185706c8e16d043238c593331cc7cd313b50"
+
+[[package]]
+name = "pin-project-lite"
+version = "0.2.17"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "a89322df9ebe1c1578d689c92318e070967d1042b512afbe49518723f4e6d5cd"
+
 [[package]]
 name = "prettyplease"
 version = "0.2.37"
@@ -222,10 +408,18 @@ version = "2.1.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "94300abf3f1ae2e2b8ffb7b58043de3d399c73fa6f4b73826402a5c457614dbe"
 
+[[package]]
+name = "rustversion"
+version = "1.0.22"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "b39cdef0fa800fc44525c84ccb54a029961a8215f9619753635a9c0d2538d46d"
+
 [[package]]
 name = "scannerbot-listener"
 version = "0.1.0"
 dependencies = [
+ "chrono",
+ "ctrlc",
  "whisper-rs",
 ]
 
@@ -241,6 +435,12 @@ version = "1.3.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "0fda2ff0d084019ba4d7c6f371c95d8fd75ce3524c3cb8fb653a3023f6323e64"
 
+[[package]]
+name = "slab"
+version = "0.4.12"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "0c790de23124f9ab44544d7ac05d60440adc586479ce501c1d6d7da3cd8c9cf5"
+
 [[package]]
 name = "syn"
 version = "2.0.117"
@@ -258,6 +458,51 @@ version = "1.0.24"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "e6e4313cd5fcd3dad5cafa179702e2b244f760991f45397d14d4ebf38247da75"
 
+[[package]]
+name = "wasm-bindgen"
+version = "0.2.121"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "49ace1d07c165b0864824eee619580c4689389afa9dc9ed3a4c75040d82e6790"
+dependencies = [
+ "cfg-if",
+ "once_cell",
+ "rustversion",
+ "wasm-bindgen-macro",
+ "wasm-bindgen-shared",
+]
+
+[[package]]
+name = "wasm-bindgen-macro"
+version = "0.2.121"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "8e68e6f4afd367a562002c05637acb8578ff2dea1943df76afb9e83d177c8578"
+dependencies = [
+ "quote",
+ "wasm-bindgen-macro-support",
+]
+
+[[package]]
+name = "wasm-bindgen-macro-support"
+version = "0.2.121"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "d95a9ec35c64b2a7cb35d3fead40c4238d0940c86d107136999567a4703259f2"
+dependencies = [
+ "bumpalo",
+ "proc-macro2",
+ "quote",
+ "syn",
+ "wasm-bindgen-shared",
+]
+
+[[package]]
+name = "wasm-bindgen-shared"
+version = "0.2.121"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "c4e0100b01e9f0d03189a92b96772a1fb998639d981193d7dbab487302513441"
+dependencies = [
+ "unicode-ident",
+]
+
 [[package]]
 name = "whisper-rs"
 version = "0.16.0"
@@ -280,8 +525,70 @@ dependencies = [
  "semver",
 ]
 
+[[package]]
+name = "windows-core"
+version = "0.62.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "b8e83a14d34d0623b51dce9581199302a221863196a1dde71a7663a4c2be9deb"
+dependencies = [
+ "windows-implement",
+ "windows-interface",
+ "windows-link",
+ "windows-result",
+ "windows-strings",
+]
+
+[[package]]
+name = "windows-implement"
+version = "0.60.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "053e2e040ab57b9dc951b72c264860db7eb3b0200ba345b4e4c3b14f67855ddf"
+dependencies = [
+ "proc-macro2",
+ "quote",
+ "syn",
+]
+
+[[package]]
+name = "windows-interface"
+version = "0.59.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "3f316c4a2570ba26bbec722032c4099d8c8bc095efccdc15688708623367e358"
+dependencies = [
+ "proc-macro2",
+ "quote",
+ "syn",
+]
+
 [[package]]
 name = "windows-link"
 version = "0.2.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "f0805222e57f7521d6a62e36fa9163bc891acd422f971defe97d64e70d0a4fe5"
+
+[[package]]
+name = "windows-result"
+version = "0.4.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "7781fa89eaf60850ac3d2da7af8e5242a5ea78d1a11c49bf2910bb5a73853eb5"
+dependencies = [
+ "windows-link",
+]
+
+[[package]]
+name = "windows-strings"
+version = "0.5.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "7837d08f69c77cf6b07689544538e017c1bfcf57e34b4c0ff58e6c2cd3b37091"
+dependencies = [
+ "windows-link",
+]
+
+[[package]]
+name = "windows-sys"
+version = "0.61.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "ae137229bcbd6cdf0f7b80a31df61766145077ddf49416a728b02cb3921ff3fc"
+dependencies = [
+ "windows-link",
+]

listener/Cargo.toml

@@ -4,4 +4,6 @@ version = "0.1.0"
 edition = "2024"
 
 [dependencies]
+chrono = "0.4.44"
+ctrlc = "3.5.2"
 whisper-rs = "0.16.0"

listener/src/audio.rs

@@ -1,14 +1,9 @@
-use std::process::{Command, Stdio};
+use std::io::Read;
+use std::process::{Child, ChildStdout, Command, Stdio};
 
 pub fn decode(input: &str) -> Result<Vec<f32>, Box<dyn std::error::Error>> {
     let output = Command::new("ffmpeg")
-        .args([
+        .args(["-i", input, "-ar", "16000", "-ac", "1", "-f", "f32le", "-"])
-            "-i", input,
-            "-ar", "16000", // resample 16kHz
-            "-ac", "1", // mono
-            "-f", "f32le", // use raw f32 little endian samples
-            "-" // stdout
-        ])
         .stderr(Stdio::null())
         .output()?;
 
@@ -19,3 +14,45 @@ pub fn decode(input: &str) -> Result<Vec<f32>, Box<dyn std::error::Error>> {
 
     Ok(audio_data)
 }
+
+pub struct LiveStream {
+    child: Child,
+    stdout: ChildStdout,
+}
+
+impl LiveStream {
+    pub fn open(source: &str) -> Result<Self, Box<dyn std::error::Error>> {
+        let mut child = Command::new("ffmpeg")
+            .args(["-f", "pulse", "-i", source, "-ar", "16000", "-ac", "1", "-f", "f32le", "pipe:1"])
+            .env("PULSE_PROP_application.name", "scannerbot-listener")
+            .stderr(Stdio::null())
+            .stdout(Stdio::piped())
+            .spawn()?;
+
+        let stdout = child.stdout.take().unwrap();
+        Ok(LiveStream { child, stdout })
+    }
+
+    // Reads exactly `secs` seconds of audio. Returns None when the stream ends.
+    pub fn next_chunk(&mut self, secs: u32) -> Result<Option<Vec<f32>>, Box<dyn std::error::Error>> {
+        let num_bytes = secs as usize * 16000 * 4;
+        let mut buf = vec![0u8; num_bytes];
+
+        match self.stdout.read_exact(&mut buf) {
+            Ok(()) => {
+                let samples = buf.chunks_exact(4)
+                    .map(|b| f32::from_le_bytes(b.try_into().unwrap()))
+                    .collect();
+                Ok(Some(samples))
+            }
+            Err(e) if e.kind() == std::io::ErrorKind::UnexpectedEof => Ok(None),
+            Err(e) => Err(e.into()),
+        }
+    }
+}
+
+impl Drop for LiveStream {
+    fn drop(&mut self) {
+        let _ = self.child.kill();
+    }
+}

listener/src/main.rs

@@ -1,38 +1,75 @@
-use whisper_rs::{WhisperContext, WhisperContextParameters, FullParams, SamplingStrategy};
+use std::fs::OpenOptions;
+use std::io::Write;
+use std::sync::atomic::{AtomicBool, Ordering};
+use std::sync::Arc;
+use chrono::{DateTime, Local};
+use whisper_rs::{FullParams, SamplingStrategy, WhisperContext, WhisperContextParameters};
 
 mod audio;
 
-fn main() -> Result<(), Box<dyn std::error::Error>> {
+const CHUNK_SECS: u32 = 30;
-    //println!("Hello, world!");
+const CHUNK_SAMPLES: usize = 16000 * CHUNK_SECS as usize;
-
-    //let audio = audio::decode("../scratch/audio/gtav_police_sample.wav")?;
-    let audio = audio::decode(&std::env::args().nth(2).unwrap())?;
-    
-    let path_to_model = std::env::args().nth(1).unwrap();
-
-    let ctx = WhisperContext::new_with_params(
-        path_to_model, 
-        WhisperContextParameters::default()
-    ).expect("failed to load model");
 
+fn transcribe_chunk(
+    state: &mut whisper_rs::WhisperState,
+    chunk: &[f32],
+    out: &mut impl Write,
+) -> Result<(), Box<dyn std::error::Error>> {
     let params = FullParams::new(SamplingStrategy::BeamSearch {
-        beam_size: 5, patience: -1.0
+        beam_size: 5,
+        patience: -1.0,
     });
-
+    let time: DateTime<Local> = Local::now();
-    let mut state = ctx.create_state().expect("failed to create state");
+    out.write_all(format!("[{}]: ", time.to_string()).as_bytes())?;
-    state
+    state.full(params, chunk)?;
-        .full(params, &audio[..])
-        .expect("failed to run model");
-
     for segment in state.as_iter() {
-        println!(
+        let line = format!("{}\n", segment);
-            "[{} - {}]: {}",
+        print!("{}", line);
-            segment.start_timestamp(),
+        out.write_all(line.as_bytes())?;
-            segment.end_timestamp(),
-            segment
-        );
     }
-
+    out.flush()?;
+    Ok(())
+}
+
+fn main() -> Result<(), Box<dyn std::error::Error>> {
+    let model_path = std::env::args().nth(1).expect("usage: listener <model> <file.wav|pulse:SOURCE> [output.txt]");
+    let audio_arg  = std::env::args().nth(2).expect("usage: listener <model> <file.wav|pulse:SOURCE> [output.txt]");
+    let output_path = std::env::args().nth(3).unwrap_or_else(|| "transcription.txt".to_string());
+
+    let running = Arc::new(AtomicBool::new(true));
+    let r = running.clone();
+    ctrlc::set_handler(move || {
+        r.store(false, Ordering::SeqCst);
+    })?;
+
+    let ctx = WhisperContext::new_with_params(&model_path, WhisperContextParameters::default())
+        .expect("failed to load model");
+    let mut state = ctx.create_state().expect("failed to create state");
+
+    let mut out = OpenOptions::new().create(true).append(true).open(&output_path)?;
+
+    eprintln!("Transcribing {} → {}  (Ctrl+C to stop)", audio_arg, output_path);
+
+    if let Some(source) = audio_arg.strip_prefix("pulse:") {
+        let mut stream = audio::LiveStream::open(source)?;
+        while running.load(Ordering::SeqCst) {
+            match stream.next_chunk(CHUNK_SECS)? {
+                Some(chunk) => transcribe_chunk(&mut state, &chunk, &mut out)?,
+                None => break,
+            }
+        }
+    } else {
+        while running.load(Ordering::SeqCst) {
+            let audio = audio::decode(&audio_arg)?;
+            for chunk in audio.chunks(CHUNK_SAMPLES) {
+                if !running.load(Ordering::SeqCst) {
+                    break;
+                }
+                transcribe_chunk(&mut state, chunk, &mut out)?;
+            }
+        }
+    }
+
+    eprintln!("Stopped.");
     Ok(())
-
 }