feat(kon): add transcription crate — transcribe-rs wrapper, model manager
- LocalEngine wraps transcribe-rs SpeechModel behind Kon's own abstraction - load_parakeet() and load_whisper() factory functions - Unified model manager: download with progress callback, check, list, path resolution - Atomic downloads: .part suffix with rename on completion - run_inference() encapsulates spawn_blocking threading - Zero Tauri dependency in this crate (progress via callback, not events) - transcribe-rs v0.3.2 with onnx + whisper-cpp features - 4 tests passing, clippy clean Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
This commit is contained in:
165
crates/transcription/src/model_manager.rs
Normal file
165
crates/transcription/src/model_manager.rs
Normal file
@@ -0,0 +1,165 @@
|
||||
use std::path::{Path, PathBuf};
|
||||
|
||||
use kon_core::error::{KonError, Result};
|
||||
use kon_core::model_registry::{find_model, ModelFile};
|
||||
use kon_core::types::{DownloadProgress, ModelId};
|
||||
|
||||
/// Resolve the models storage directory.
|
||||
/// Windows: %LOCALAPPDATA%/kon/models
|
||||
/// Unix: ~/.kon/models
|
||||
pub fn models_dir() -> PathBuf {
|
||||
if cfg!(target_os = "windows") {
|
||||
let local_app_data = std::env::var("LOCALAPPDATA")
|
||||
.unwrap_or_else(|_| ".".to_string());
|
||||
PathBuf::from(local_app_data).join("kon").join("models")
|
||||
} else {
|
||||
dirs_path().join("models")
|
||||
}
|
||||
}
|
||||
|
||||
fn dirs_path() -> PathBuf {
|
||||
if cfg!(target_os = "windows") {
|
||||
let local_app_data = std::env::var("LOCALAPPDATA")
|
||||
.unwrap_or_else(|_| ".".to_string());
|
||||
PathBuf::from(local_app_data).join("kon")
|
||||
} else {
|
||||
let home =
|
||||
std::env::var("HOME").unwrap_or_else(|_| "/tmp".to_string());
|
||||
PathBuf::from(home).join(".kon")
|
||||
}
|
||||
}
|
||||
|
||||
/// Get the directory path where a specific model's files are stored.
|
||||
pub fn model_dir(id: &ModelId) -> PathBuf {
|
||||
models_dir().join(id.as_str())
|
||||
}
|
||||
|
||||
/// Check whether all files for a model have been downloaded.
|
||||
pub fn is_downloaded(id: &ModelId) -> bool {
|
||||
let entry = match find_model(id) {
|
||||
Some(e) => e,
|
||||
None => return false,
|
||||
};
|
||||
let dir = model_dir(id);
|
||||
entry.files.iter().all(|f| dir.join(f.filename).exists())
|
||||
}
|
||||
|
||||
/// List all downloaded model IDs.
|
||||
pub fn list_downloaded() -> Vec<ModelId> {
|
||||
kon_core::model_registry::all_models()
|
||||
.iter()
|
||||
.filter(|m| is_downloaded(&m.id))
|
||||
.map(|m| m.id.clone())
|
||||
.collect()
|
||||
}
|
||||
|
||||
/// Download all files for a model, calling the progress callback per chunk.
|
||||
/// Files are downloaded to a .part suffix and atomically renamed on completion.
|
||||
pub async fn download(
|
||||
id: &ModelId,
|
||||
progress: impl Fn(DownloadProgress) + Send + 'static,
|
||||
) -> Result<()> {
|
||||
let entry = find_model(id)
|
||||
.ok_or_else(|| KonError::ModelNotFound(id.clone()))?;
|
||||
|
||||
let dir = model_dir(id);
|
||||
std::fs::create_dir_all(&dir)?;
|
||||
|
||||
for file in &entry.files {
|
||||
let dest = dir.join(file.filename);
|
||||
if dest.exists() {
|
||||
continue;
|
||||
}
|
||||
download_file(file, &dest, id, &progress).await?;
|
||||
}
|
||||
|
||||
Ok(())
|
||||
}
|
||||
|
||||
async fn download_file(
|
||||
file: &ModelFile,
|
||||
dest: &Path,
|
||||
model_id: &ModelId,
|
||||
progress: &(impl Fn(DownloadProgress) + Send),
|
||||
) -> Result<()> {
|
||||
use futures_util::StreamExt;
|
||||
|
||||
let part_path = dest.with_extension(
|
||||
dest.extension()
|
||||
.map(|e| format!("{}.part", e.to_string_lossy()))
|
||||
.unwrap_or_else(|| "part".to_string()),
|
||||
);
|
||||
|
||||
let client = reqwest::Client::builder()
|
||||
.timeout(std::time::Duration::from_secs(30))
|
||||
.build()
|
||||
.map_err(|e| KonError::DownloadFailed(e.to_string()))?;
|
||||
|
||||
let response = client
|
||||
.get(file.url)
|
||||
.send()
|
||||
.await
|
||||
.map_err(|e| KonError::DownloadFailed(e.to_string()))?;
|
||||
|
||||
let total_bytes = response.content_length().unwrap_or(0);
|
||||
let mut stream = response.bytes_stream();
|
||||
let mut downloaded: u64 = 0;
|
||||
let mut last_percent: u8 = 0;
|
||||
|
||||
let mut out = std::fs::File::create(&part_path)?;
|
||||
|
||||
while let Some(chunk) = stream.next().await {
|
||||
let chunk = chunk
|
||||
.map_err(|e| KonError::DownloadFailed(e.to_string()))?;
|
||||
std::io::Write::write_all(&mut out, &chunk)?;
|
||||
downloaded += chunk.len() as u64;
|
||||
|
||||
let percent = if total_bytes > 0 {
|
||||
((downloaded as f64 / total_bytes as f64) * 100.0) as u8
|
||||
} else {
|
||||
0
|
||||
};
|
||||
|
||||
if percent != last_percent {
|
||||
last_percent = percent;
|
||||
progress(DownloadProgress {
|
||||
model_id: model_id.clone(),
|
||||
file_name: file.filename.to_string(),
|
||||
bytes_downloaded: downloaded,
|
||||
total_bytes,
|
||||
percent,
|
||||
});
|
||||
}
|
||||
}
|
||||
|
||||
drop(out);
|
||||
std::fs::rename(&part_path, dest)?;
|
||||
|
||||
Ok(())
|
||||
}
|
||||
|
||||
#[cfg(test)]
|
||||
mod tests {
|
||||
use super::*;
|
||||
|
||||
#[test]
|
||||
fn model_dir_returns_correct_path() {
|
||||
let id = ModelId::new("whisper-tiny-en");
|
||||
let path = model_dir(&id);
|
||||
assert!(path.to_string_lossy().contains("whisper-tiny-en"));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn is_downloaded_returns_false_for_missing_model() {
|
||||
let id = ModelId::new("nonexistent-model");
|
||||
assert!(!is_downloaded(&id));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn list_downloaded_returns_empty_when_no_models() {
|
||||
let list = list_downloaded();
|
||||
// In test environment, no models are downloaded
|
||||
// This just verifies the function doesn't panic
|
||||
assert!(list.len() <= kon_core::model_registry::all_models().len());
|
||||
}
|
||||
}
|
||||
Reference in New Issue
Block a user