Warm up pyannote and FunASR runtimes
PR and Push Build/Test / build-and-test (push) Successful in 6m48s

This commit is contained in:
2026-05-28 13:05:27 +02:00
parent 7ff93b73b3
commit c46c587e65
14 changed files with 696 additions and 20 deletions
@@ -82,6 +82,58 @@ public sealed class PyannoteTranscriptFinalizer
return segments;
}
public async Task WarmUpAsync(
PyannoteDiarizationOptions diarization,
CancellationToken cancellationToken)
{
if (!diarization.Enabled)
{
return;
}
var token = ResolveToken(diarization);
if (string.IsNullOrWhiteSpace(token))
{
logger.LogWarning(
"Pyannote warm-up is enabled but no Hugging Face token is configured directly or via {TokenEnv}",
diarization.TokenEnv);
return;
}
var modelsFolder = VaultPath.Resolve(diarization.ModelsFolder);
Directory.CreateDirectory(modelsFolder);
using var timeoutSource = diarization.CommandTimeout > TimeSpan.Zero
? new CancellationTokenSource(diarization.CommandTimeout)
: null;
using var linkedSource = timeoutSource is null
? null
: CancellationTokenSource.CreateLinkedTokenSource(cancellationToken, timeoutSource.Token);
try
{
if (diarization.BuildImage)
{
await EnsureDockerImageAsync(diarization, modelsFolder, linkedSource?.Token ?? cancellationToken);
}
var result = await commandRunner.RunAsync(
diarization.DockerCommand,
BuildWarmUpDockerArguments(diarization, modelsFolder),
linkedSource?.Token ?? cancellationToken,
new Dictionary<string, string> { ["HF_TOKEN"] = token });
if (result.ExitCode != 0)
{
throw new InvalidOperationException(
$"pyannote warm-up failed with exit code {result.ExitCode}: {result.StandardError}");
}
}
catch (OperationCanceledException) when (!cancellationToken.IsCancellationRequested && timeoutSource?.IsCancellationRequested == true)
{
throw new TimeoutException(
$"pyannote warm-up timed out after {diarization.CommandTimeout}.");
}
}
private async Task<CommandResult> RunDiarizationAsync(
string fullAudioPath,
string token,
@@ -189,6 +241,33 @@ public sealed class PyannoteTranscriptFinalizer
];
}
private string[] BuildWarmUpDockerArguments(
PyannoteDiarizationOptions diarization,
string modelsFolder)
{
return
[
"run",
"--rm",
"-e",
"HF_TOKEN",
"-v",
$"{modelsFolder}:/workspace/cache",
"-e",
"HF_HOME=/workspace/cache/huggingface",
"-e",
"XDG_CACHE_HOME=/workspace/cache",
"-e",
"PIP_CACHE_DIR=/workspace/cache/pip",
"-e",
"TORCH_HOME=/workspace/cache/torch",
diarization.Image,
"sh",
"-lc",
BuildWarmUpPythonCommand(diarization)
];
}
private static string BuildPythonCommand(
PyannoteDiarizationOptions diarization,
SpeechRecognitionPipelineOptions pipelineOptions)
@@ -217,6 +296,21 @@ public sealed class PyannoteTranscriptFinalizer
+ "python /tmp/meeting_assistant_pyannote.py";
}
private static string BuildWarmUpPythonCommand(PyannoteDiarizationOptions diarization)
{
var model = diarization.Model;
return
"cat > /tmp/meeting_assistant_pyannote_warmup.py <<'PY'\n"
+ "import os\n"
+ "import torch\n"
+ "from pyannote.audio import Pipeline\n"
+ $"pipeline = Pipeline.from_pretrained({JsonSerializer.Serialize(model)}, token=os.environ.get('HF_TOKEN'))\n"
+ "pipeline.to(torch.device('cpu'))\n"
+ "print('pyannote warm-up complete')\n"
+ "PY\n"
+ "python /tmp/meeting_assistant_pyannote_warmup.py";
}
private static string BuildPipelineInvocation(SpeechRecognitionPipelineOptions pipelineOptions)
{
return pipelineOptions.NumSpeakers is > 0