feat: 优化音频传输参数

This commit is contained in:
Del Wang
2025-12-31 22:53:33 +08:00
committed by Del
parent 392d8bc21b
commit 8e788f4b47
9 changed files with 195 additions and 328 deletions
+2 -1
View File
@@ -1 +1,2 @@
*.mp3
*.mp3
*.wav
+1 -198
View File
@@ -2,15 +2,6 @@
# It is not intended for manual editing.
version = 4
[[package]]
name = "aho-corasick"
version = "1.1.4"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "ddd31a130427c27518df266943a5308ed92d4b226cc639f5a8f1002816174301"
dependencies = [
"memchr",
]
[[package]]
name = "alsa"
version = "0.11.0"
@@ -33,56 +24,6 @@ dependencies = [
"pkg-config",
]
[[package]]
name = "anstream"
version = "0.6.21"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "43d5b281e737544384e969a5ccad3f1cdd24b48086a0fc1b2a5262a26b8f4f4a"
dependencies = [
"anstyle",
"anstyle-parse",
"anstyle-query",
"anstyle-wincon",
"colorchoice",
"is_terminal_polyfill",
"utf8parse",
]
[[package]]
name = "anstyle"
version = "1.0.13"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "5192cca8006f1fd4f7237516f40fa183bb07f8fbdfedaa0036de5ea9b0b45e78"
[[package]]
name = "anstyle-parse"
version = "0.2.7"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "4e7644824f0aa2c7b9384579234ef10eb7efb6a0deb83f9630a49594dd9c15c2"
dependencies = [
"utf8parse",
]
[[package]]
name = "anstyle-query"
version = "1.1.5"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "40c48f72fd53cd289104fc64099abca73db4166ad86ea0b4341abe65af83dadc"
dependencies = [
"windows-sys 0.61.2",
]
[[package]]
name = "anstyle-wincon"
version = "3.0.11"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "291e6a250ff86cd4a820112fb8898808a366d8f9f58ce16d1f538353ad55747d"
dependencies = [
"anstyle",
"once_cell_polyfill",
"windows-sys 0.61.2",
]
[[package]]
name = "anyhow"
version = "1.0.100"
@@ -179,12 +120,6 @@ dependencies = [
"thiserror",
]
[[package]]
name = "colorchoice"
version = "1.0.4"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "b05b61dc5112cbb17e4b6cd61790d9845d13888356391624cbe7e41efeac1e75"
[[package]]
name = "critical-section"
version = "1.2.0"
@@ -212,29 +147,6 @@ dependencies = [
"cfg-if",
]
[[package]]
name = "env_filter"
version = "0.1.4"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "1bf3c259d255ca70051b30e2e95b5446cdb8949ac4cd22c0d7fd634d89f568e2"
dependencies = [
"log",
"regex",
]
[[package]]
name = "env_logger"
version = "0.11.8"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "13c863f0904021b108aa8b2f55046443e6b1ebde8fd4a15c399893aae4fa069f"
dependencies = [
"anstream",
"anstyle",
"env_filter",
"jiff",
"log",
]
[[package]]
name = "errno"
version = "0.3.14"
@@ -242,7 +154,7 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "39cab71617ae0d63f51a36d69f866391735b51691dbda63cf6f96d042b63efeb"
dependencies = [
"libc",
"windows-sys 0.61.2",
"windows-sys 0.60.2",
]
[[package]]
@@ -286,9 +198,6 @@ version = "0.1.0"
dependencies = [
"alsa",
"anyhow",
"byteorder",
"env_logger",
"log",
"opus",
"postcard",
"serde",
@@ -296,36 +205,6 @@ dependencies = [
"tokio",
]
[[package]]
name = "is_terminal_polyfill"
version = "1.70.2"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "a6cb138bb79a146c1bd460005623e142ef0181e3d0219cb493e02f7d08a35695"
[[package]]
name = "jiff"
version = "0.2.17"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "a87d9b8105c23642f50cbbae03d1f75d8422c5cb98ce7ee9271f7ff7505be6b8"
dependencies = [
"jiff-static",
"log",
"portable-atomic",
"portable-atomic-util",
"serde_core",
]
[[package]]
name = "jiff-static"
version = "0.2.17"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "b787bebb543f8969132630c51fd0afab173a86c6abae56ff3b9e5e3e3f9f6e58"
dependencies = [
"proc-macro2",
"quote",
"syn",
]
[[package]]
name = "lazy_static"
version = "1.5.0"
@@ -353,12 +232,6 @@ version = "0.4.29"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "5e5032e24019045c762d3c0f28f5b6b8bbf38563a65908389bf7978758920897"
[[package]]
name = "memchr"
version = "2.7.6"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "f52b00d39961fc5b2736ea853c9cc86238e165017a493d1d5c8eac6bdc4cc273"
[[package]]
name = "mio"
version = "1.1.1"
@@ -370,12 +243,6 @@ dependencies = [
"windows-sys 0.61.2",
]
[[package]]
name = "once_cell_polyfill"
version = "1.70.2"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "384b8ab6d37215f3c5301a95a4accb5d64aa607f1fcb26a11b5303878451b4fe"
[[package]]
name = "opus"
version = "0.3.0"
@@ -421,21 +288,6 @@ version = "0.3.32"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "7edddbd0b52d732b21ad9a5fab5c704c14cd949e5e9a1ec5929a24fded1b904c"
[[package]]
name = "portable-atomic"
version = "1.13.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "f89776e4d69bb58bc6993e99ffa1d11f228b839984854c7daeb5d37f87cbe950"
[[package]]
name = "portable-atomic-util"
version = "0.2.4"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "d8a2f0d8d040d7848a709caf78912debcc3f33ee4b3cac47d73d1e1069e83507"
dependencies = [
"portable-atomic",
]
[[package]]
name = "postcard"
version = "1.1.3"
@@ -476,35 +328,6 @@ dependencies = [
"bitflags 2.10.0",
]
[[package]]
name = "regex"
version = "1.12.2"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "843bc0191f75f3e22651ae5f1e72939ab2f72a4bc30fa80a066bd66edefc24d4"
dependencies = [
"aho-corasick",
"memchr",
"regex-automata",
"regex-syntax",
]
[[package]]
name = "regex-automata"
version = "0.4.13"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "5276caf25ac86c8d810222b3dbb938e512c55c6831a10f3e6ed1c93b84041f1c"
dependencies = [
"aho-corasick",
"memchr",
"regex-syntax",
]
[[package]]
name = "regex-syntax"
version = "0.8.8"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "7a2d987857b319362043e95f5353c0535c1f58eec5336fdfcf626430af7def58"
[[package]]
name = "rustc_version"
version = "0.4.1"
@@ -616,7 +439,6 @@ dependencies = [
"symphonia-codec-pcm",
"symphonia-codec-vorbis",
"symphonia-core",
"symphonia-format-isomp4",
"symphonia-format-mkv",
"symphonia-format-ogg",
"symphonia-format-riff",
@@ -691,19 +513,6 @@ dependencies = [
"log",
]
[[package]]
name = "symphonia-format-isomp4"
version = "0.5.5"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "243739585d11f81daf8dac8d9f3d18cc7898f6c09a259675fc364b382c30e0a5"
dependencies = [
"encoding_rs",
"log",
"symphonia-core",
"symphonia-metadata",
"symphonia-utils-xiph",
]
[[package]]
name = "symphonia-format-mkv"
version = "0.5.5"
@@ -828,12 +637,6 @@ version = "1.0.22"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "9312f7c4f6ff9069b165498234ce8be658059c6728633667c526e27dc2cf1df5"
[[package]]
name = "utf8parse"
version = "0.2.2"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "06abde3611657adf66d383f00b093d7faecc7fa57071cce2578660c9f1010821"
[[package]]
name = "wasi"
version = "0.11.1+wasi-snapshot-preview1"
+4 -5
View File
@@ -14,13 +14,12 @@ debug = false
[dependencies]
opus = "0.3"
anyhow = "1.0"
tokio = { version = "1.47", features = ["full"] }
symphonia = { version = "0.5", features = ["mp3", "isomp4"] }
tokio = { version = "1.48", features = ["full"] }
serde = { version = "1.0", features = ["derive"] }
postcard = { version = "1.0", features = ["alloc", "use-std"] }
log = "0.4"
env_logger = "0.11"
byteorder = "1.5"
[target.'cfg(not(target_os = "linux"))'.dependencies]
symphonia = { version = "0.5", features = ["mp3", "wav", "pcm"] }
[target.'cfg(target_os = "linux")'.dependencies]
alsa = "0.11"
+18 -15
View File
@@ -2,24 +2,27 @@
set -e
# SSH_PASSWORD=open-xiaoai
SSH_PASSWORD=open-xiaoai
# # 1. 编译 demo
# echo "Compiling hello demo..."
# docker run --rm -v $(pwd):/app/hello open-xiaoai-runtime \
# cargo build --manifest-path hello/Cargo.toml --target armv7-unknown-linux-gnueabihf --bin client --release
# 1. 编译 client
echo "Compiling client..."
docker run --rm -v $(pwd):/app/hello open-xiaoai-runtime \
cargo build --manifest-path hello/Cargo.toml --target armv7-unknown-linux-gnueabihf --bin client --release
# # 2. 上传二进制文件到小爱音箱
# function upload_to_xiaoai() {
# local binary_name=$1
# local ip=$2
# dd if=target/armv7-unknown-linux-gnueabihf/release/$binary_name \
# | sshpass -p $SSH_PASSWORD ssh -o HostKeyAlgorithms=+ssh-rsa root@$ip "dd of=/data/$binary_name" \
# && echo "✅ Uploaded $binary_name to $ip"
# }
# 2. 上传 client 到小爱音箱
function upload_to_xiaoai() {
local binary_name=$1
local ip=$2
dd if=target/armv7-unknown-linux-gnueabihf/release/$binary_name \
| sshpass -p $SSH_PASSWORD ssh -o HostKeyAlgorithms=+ssh-rsa root@$ip "dd of=/data/$binary_name" \
&& echo "✅ Uploaded $binary_name to $ip"
}
# upload_to_xiaoai client 192.168.31.153 # left
# upload_to_xiaoai client 192.168.31.235 # right
upload_to_xiaoai client 192.168.31.153 # left
upload_to_xiaoai client 192.168.31.235 # right
# 3. 编译 server
cargo build --bin server --release
./target/release/server
# dd if=test.wav | sshpass -p open-xiaoai ssh -o HostKeyAlgorithms=+ssh-rsa root@192.168.31.235 "dd of=/tmp/test.wav"
+1 -1
View File
@@ -10,7 +10,7 @@ pub struct OpusCodec {
impl OpusCodec {
pub fn new(config: &AudioConfig) -> Result<Self> {
let channels = if config.channels == 1 { Channels::Mono } else { Channels::Stereo };
let mut encoder = Encoder::new(config.sample_rate, channels, Application::Voip)
let mut encoder = Encoder::new(config.sample_rate, channels, Application::Audio)
.context("Failed to create Opus encoder")?;
encoder.set_bitrate(Bitrate::Bits(config.bitrate))?;
+8 -8
View File
@@ -1,12 +1,12 @@
#[cfg(target_os = "linux")]
pub mod recorder;
#[cfg(target_os = "linux")]
pub mod player;
pub mod codec;
pub mod player;
pub mod reader;
pub mod recorder;
pub use codec::*;
#[cfg(target_os = "linux")]
pub use recorder::AudioRecorder;
pub use player::*;
#[cfg(not(target_os = "linux"))]
pub use reader::*;
#[cfg(target_os = "linux")]
pub use player::AudioPlayer;
pub use codec::OpusCodec;
pub use recorder::*;
+140
View File
@@ -0,0 +1,140 @@
#![cfg(not(target_os = "linux"))]
use anyhow::{Context, Result};
use std::fs::File;
use std::path::Path;
use symphonia::core::audio::SampleBuffer;
use symphonia::core::codecs::{Decoder, DecoderOptions};
use symphonia::core::formats::{FormatOptions, FormatReader};
use symphonia::core::io::MediaSourceStream;
use symphonia::core::meta::MetadataOptions;
use symphonia::core::probe::Hint;
pub struct AudioReader {
format: Box<dyn FormatReader>,
decoder: Box<dyn Decoder>,
track_id: u32,
sample_buf: Option<SampleBuffer<i16>>,
channels: usize,
left_buffer: Vec<i16>,
right_buffer: Vec<i16>,
}
impl AudioReader {
pub fn new(path: &str) -> Result<Self> {
let src =
File::open(Path::new(path)).context(format!("Failed to open audio file: {}", path))?;
let mss = MediaSourceStream::new(Box::new(src), Default::default());
let mut hint = Hint::new();
if path.ends_with(".wav") {
hint.with_extension("wav");
} else if path.ends_with(".mp3") {
hint.with_extension("mp3");
}
let probed = symphonia::default::get_probe()
.format(
&hint,
mss,
&FormatOptions::default(),
&MetadataOptions::default(),
)
.context("Failed to probe audio format")?;
let format = probed.format;
let track = format
.tracks()
.iter()
.find(|t| t.codec_params.codec != symphonia::core::codecs::CODEC_TYPE_NULL)
.context("No supported audio track found")?;
let track_id = track.id;
let decoder = symphonia::default::get_codecs()
.make(&track.codec_params, &DecoderOptions::default())
.context("Failed to create decoder")?;
let channels = track.codec_params.channels.map(|c| c.count()).unwrap_or(1);
Ok(Self {
format,
decoder,
track_id,
sample_buf: None,
channels,
left_buffer: Vec::new(),
right_buffer: Vec::new(),
})
}
pub fn read_chunk(&mut self, chunk_size: usize) -> Result<Option<(Vec<i16>, Vec<i16>)>> {
while self.left_buffer.len() < chunk_size {
if let Some((l, r)) = self.read_frame_internal()? {
self.left_buffer.extend(l);
self.right_buffer.extend(r);
} else {
break;
}
}
if self.left_buffer.is_empty() {
return Ok(None);
}
let actual_size = std::cmp::min(chunk_size, self.left_buffer.len());
let left = self.left_buffer.drain(0..actual_size).collect();
let right = self.right_buffer.drain(0..actual_size).collect();
Ok(Some((left, right)))
}
fn read_frame_internal(&mut self) -> Result<Option<(Vec<i16>, Vec<i16>)>> {
loop {
let packet = match self.format.next_packet() {
Ok(packet) => packet,
Err(symphonia::core::errors::Error::IoError(ref e))
if e.kind() == std::io::ErrorKind::UnexpectedEof =>
{
return Ok(None);
}
Err(e) => return Err(e.into()),
};
if packet.track_id() != self.track_id {
continue;
}
let decoded = self
.decoder
.decode(&packet)
.context("Failed to decode packet")?;
if self.sample_buf.is_none() {
self.sample_buf = Some(SampleBuffer::<i16>::new(
decoded.capacity() as u64,
*decoded.spec(),
));
}
if let Some(buf) = self.sample_buf.as_mut() {
buf.copy_interleaved_ref(decoded);
let samples = buf.samples();
let mut left = Vec::with_capacity(samples.len() / self.channels);
let mut right = Vec::with_capacity(samples.len() / self.channels);
if self.channels == 2 {
for i in (0..samples.len()).step_by(2) {
left.push(samples[i]);
right.push(samples[i + 1]);
}
} else {
for &s in samples {
left.push(s);
right.push(s);
}
}
return Ok(Some((left, right)));
}
}
}
}
+1 -1
View File
@@ -23,7 +23,6 @@ async fn main() -> Result<()> {
#[cfg(target_os = "linux")]
{
env_logger::init();
let args: Vec<String> = env::args().collect();
if args.len() < 2 {
eprintln!("Usage: {} [left|right]", args[0]);
@@ -39,6 +38,7 @@ async fn main() -> Result<()> {
sample_rate: 48000,
channels: 1,
frame_size: 960,
bitrate: 32000,
..AudioConfig::default()
};
+20 -99
View File
@@ -1,29 +1,21 @@
use anyhow::{Context, Result};
use hello::audio::OpusCodec;
use anyhow::Result;
use hello::audio::{AudioReader, OpusCodec};
use hello::config::AudioConfig;
use hello::net::{AudioPacket, ChannelRole, ControlPacket, Discovery, SERVER_PORT};
use hello::sync::now_us;
use std::collections::HashMap;
use std::fs::File;
use std::path::Path;
use std::sync::Arc;
use symphonia::core::audio::SampleBuffer;
use symphonia::core::codecs::DecoderOptions;
use symphonia::core::formats::FormatOptions;
use symphonia::core::io::MediaSourceStream;
use symphonia::core::meta::MetadataOptions;
use symphonia::core::probe::Hint;
use tokio::io::{AsyncReadExt, AsyncWriteExt};
use tokio::net::{TcpListener, TcpStream};
use tokio::sync::Mutex;
#[tokio::main]
async fn main() -> Result<()> {
env_logger::init();
let config = AudioConfig {
sample_rate: 48000,
channels: 1,
frame_size: 960, // 20ms at 48kHz
bitrate: 32000, // 32kbps
..AudioConfig::default()
};
@@ -76,34 +68,17 @@ async fn main() -> Result<()> {
println!("Both clients connected. Starting stream in 1s...");
tokio::time::sleep(tokio::time::Duration::from_secs(1)).await;
stream_mp3("test.mp3", &config, clients).await?;
stream_audio("test.mp3", &config, clients).await?;
Ok(())
}
async fn stream_mp3(
async fn stream_audio(
path: &str,
config: &AudioConfig,
clients: Arc<Mutex<HashMap<ChannelRole, TcpStream>>>,
) -> Result<()> {
let src = File::open(Path::new(path)).context("Failed to open test.mp3")?;
let mss = MediaSourceStream::new(Box::new(src), Default::default());
let probed = symphonia::default::get_probe().format(
&Hint::new(),
mss,
&FormatOptions::default(),
&MetadataOptions::default(),
)?;
let mut format = probed.format;
let track = format
.tracks()
.iter()
.find(|t| t.codec_params.codec == symphonia::core::codecs::CODEC_TYPE_MP3)
.context("No track")?;
let mut decoder =
symphonia::default::get_codecs().make(&track.codec_params, &DecoderOptions::default())?;
let track_id = track.id;
let mut reader = AudioReader::new(path)?;
let mut left_codec = OpusCodec::new(config)?;
let mut right_codec = OpusCodec::new(config)?;
@@ -113,76 +88,22 @@ async fn stream_mp3(
let frame_duration_us =
(config.frame_size as f64 / config.sample_rate as f64 * 1_000_000.0) as u128;
let mut sample_buf = None;
loop {
let packet = match format.next_packet() {
Ok(packet) => packet,
Err(_) => break,
};
if packet.track_id() != track_id {
continue;
while let Some((left_pcm, right_pcm)) = reader.read_chunk(config.frame_size)? {
if left_pcm.len() < config.frame_size {
break;
}
let decoded = decoder.decode(&packet)?;
if sample_buf.is_none() {
sample_buf = Some(SampleBuffer::<i16>::new(
decoded.capacity() as u64,
*decoded.spec(),
));
}
if let Some(buf) = sample_buf.as_mut() {
buf.copy_interleaved_ref(decoded.clone());
let spec = decoded.spec();
let num_channels = spec.channels.count();
if num_channels == 2 {
for chunk in buf.samples().chunks(config.frame_size * 2) {
if chunk.len() < config.frame_size * 2 {
break;
}
let mut left_pcm = vec![0i16; config.frame_size];
let mut right_pcm = vec![0i16; config.frame_size];
for i in 0..config.frame_size {
left_pcm[i] = chunk[i * 2];
right_pcm[i] = chunk[i * 2 + 1];
}
send_packets(
&clients,
&mut left_codec,
&mut right_codec,
&left_pcm,
&right_pcm,
current_frame_ts,
)
.await?;
current_frame_ts += frame_duration_us;
pace(current_frame_ts).await;
}
} else {
for chunk in buf.samples().chunks(config.frame_size) {
if chunk.len() < config.frame_size {
break;
}
send_packets(
&clients,
&mut left_codec,
&mut right_codec,
chunk,
chunk,
current_frame_ts,
)
.await?;
current_frame_ts += frame_duration_us;
pace(current_frame_ts).await;
}
}
}
send_packets(
&clients,
&mut left_codec,
&mut right_codec,
&left_pcm,
&right_pcm,
current_frame_ts,
)
.await?;
current_frame_ts += frame_duration_us;
pace(current_frame_ts).await;
}
Ok(())
}