Files
meeting-assistant/MeetingAssistant/Speakers/VenvResemblyzerVoiceEncoder.cs

392 lines
14 KiB
C#

using System.Globalization;
using System.Security.Cryptography;
using System.Text;
using System.Text.Json;
using System.Text.RegularExpressions;
using MeetingAssistant.Transcription;
using Microsoft.Extensions.Options;
namespace MeetingAssistant.Speakers;
public interface IResemblyzerVoiceEncoder
{
Task<IReadOnlyList<float[]>> EncodeAsync(
IReadOnlyList<byte[]> wavSamples,
CancellationToken cancellationToken);
Task WarmUpAsync(CancellationToken cancellationToken);
}
public sealed partial class VenvResemblyzerVoiceEncoder : IResemblyzerVoiceEncoder
{
private const string EnvironmentSchemaVersion = "venv-v2";
private const string JsonStart = "__MEETING_ASSISTANT_RESEMBLYZER_JSON_START__";
private const string JsonEnd = "__MEETING_ASSISTANT_RESEMBLYZER_JSON_END__";
private const string NumpyBeforePython313Requirement = "numpy<2; python_version < '3.13'";
private const string NumpyFromPython313Requirement = "numpy>=2,<3; python_version >= '3.13'";
private const string LibrosaRequirement = "librosa>=0.9.1";
private const string ScipyRequirement = "scipy>=1.2.1";
private readonly SemaphoreSlim commandLock = new(1, 1);
private readonly ICommandRunner commandRunner;
private readonly ResemblyzerSpeakerRecognitionOptions options;
private readonly ILogger<VenvResemblyzerVoiceEncoder> logger;
private string? verifiedEnvironmentPythonPath;
public VenvResemblyzerVoiceEncoder(
ICommandRunner commandRunner,
IOptions<MeetingAssistantOptions> options,
ILogger<VenvResemblyzerVoiceEncoder> logger)
{
this.commandRunner = commandRunner;
this.options = options.Value.SpeakerIdentification.Resemblyzer;
this.logger = logger;
}
public async Task<IReadOnlyList<float[]>> EncodeAsync(
IReadOnlyList<byte[]> wavSamples,
CancellationToken cancellationToken)
{
if (wavSamples.Count == 0)
{
return [];
}
if (wavSamples.Any(sample => sample.Length == 0))
{
throw new InvalidDataException("Resemblyzer cannot encode an empty WAV sample.");
}
var runtimeFolder = VaultPath.Resolve(options.RuntimeFolder);
var inputFolder = Path.Combine(runtimeFolder, "input", Guid.NewGuid().ToString("N"));
Directory.CreateDirectory(inputFolder);
try
{
for (var index = 0; index < wavSamples.Count; index++)
{
await File.WriteAllBytesAsync(
Path.Combine(inputFolder, $"{index:D4}.wav"),
wavSamples[index],
cancellationToken);
}
await commandLock.WaitAsync(cancellationToken);
try
{
return await RunEncodingAsync(inputFolder, wavSamples.Count, cancellationToken);
}
finally
{
commandLock.Release();
}
}
finally
{
try
{
Directory.Delete(inputFolder, recursive: true);
}
catch (DirectoryNotFoundException)
{
}
catch (IOException exception)
{
logger.LogWarning(exception, "Could not remove Resemblyzer temporary input folder {InputFolder}", inputFolder);
}
catch (UnauthorizedAccessException exception)
{
logger.LogWarning(exception, "Could not remove Resemblyzer temporary input folder {InputFolder}", inputFolder);
}
}
}
private async Task<IReadOnlyList<float[]>> RunEncodingAsync(
string inputFolder,
int expectedCount,
CancellationToken cancellationToken)
{
return await RunWithTimeoutAsync(async token =>
{
var pythonPath = await EnsureEnvironmentAsync(token);
var scriptPath = Path.Combine(VaultPath.Resolve(options.RuntimeFolder), "encode.py");
await File.WriteAllTextAsync(scriptPath, BuildEncodingScript(), token);
var result = await RunRequiredAsync(
pythonPath,
[scriptPath, Path.GetFullPath(inputFolder)],
"encoding",
token);
return ParseAndValidateVectors(result.StandardOutput, expectedCount);
}, cancellationToken);
}
public async Task WarmUpAsync(CancellationToken cancellationToken)
{
await commandLock.WaitAsync(cancellationToken);
try
{
await RunWithTimeoutAsync(async token =>
{
await EnsureEnvironmentAsync(token);
return true;
}, cancellationToken);
}
finally
{
commandLock.Release();
}
}
private async Task<string> EnsureEnvironmentAsync(CancellationToken cancellationToken)
{
ValidateDependencySettings();
var runtimeFolder = VaultPath.Resolve(options.RuntimeFolder);
var environmentFolder = Path.Combine(runtimeFolder, "venv", BuildEnvironmentKey());
var pythonPath = GetEnvironmentPythonPath(environmentFolder);
var readyPath = Path.Combine(environmentFolder, ".ready");
if (string.Equals(verifiedEnvironmentPythonPath, pythonPath, StringComparison.OrdinalIgnoreCase)
&& File.Exists(pythonPath)
&& File.Exists(readyPath))
{
return pythonPath;
}
if (File.Exists(pythonPath) && File.Exists(readyPath))
{
var verification = await commandRunner.RunAsync(
pythonPath,
WarmupArguments,
cancellationToken);
if (verification.ExitCode == 0)
{
verifiedEnvironmentPythonPath = pythonPath;
return pythonPath;
}
logger.LogWarning(
"Existing Resemblyzer environment verification failed with exit code {ExitCode}: {Error}. Reprovisioning it.",
verification.ExitCode,
verification.StandardError);
File.Delete(readyPath);
}
Directory.CreateDirectory(environmentFolder);
await RunRequiredAsync(
options.PythonCommand,
["-m", "venv", "--clear", environmentFolder],
"virtual environment creation",
cancellationToken);
await RunRequiredAsync(
pythonPath,
["-m", "pip", "install", "--upgrade", "pip"],
"pip upgrade",
cancellationToken);
await RunRequiredAsync(
pythonPath,
[
"-m", "pip", "install",
"--index-url", options.TorchIndexUrl,
TorchRequirement
],
"CPU PyTorch installation",
cancellationToken);
await RunRequiredAsync(
pythonPath,
[
"-m", "pip", "install",
.. RuntimeDependencyRequirements
],
"Resemblyzer dependency installation",
cancellationToken);
await RunRequiredAsync(
pythonPath,
[
"-m", "pip", "install", "--no-deps",
ResemblyzerRequirement
],
"Resemblyzer installation",
cancellationToken);
await RunRequiredAsync(
pythonPath,
WarmupArguments,
"environment verification",
cancellationToken);
await File.WriteAllTextAsync(readyPath, BuildEnvironmentKey(), cancellationToken);
verifiedEnvironmentPythonPath = pythonPath;
return pythonPath;
}
private async Task<CommandResult> RunRequiredAsync(
string fileName,
IReadOnlyList<string> arguments,
string operation,
CancellationToken cancellationToken)
{
var result = await commandRunner.RunAsync(fileName, arguments, cancellationToken);
ThrowIfFailed(result, operation);
return result;
}
private static string BuildEncodingScript()
{
return
"import json\n"
+ "import sys\n"
+ "import numpy as np\n"
+ "from pathlib import Path\n"
+ "from resemblyzer import VoiceEncoder, preprocess_wav\n"
+ "encoder = VoiceEncoder('cpu', verbose=False)\n"
+ "vectors = []\n"
+ "for path in sorted(Path(sys.argv[1]).glob('*.wav')):\n"
+ " wav = preprocess_wav(path)\n"
+ " vector = encoder.embed_utterance(wav)\n"
+ " vectors.append(np.asarray(vector, dtype=np.float32).tolist())\n"
+ $"print('{JsonStart}')\n"
+ "print(json.dumps(vectors, allow_nan=False))\n"
+ $"print('{JsonEnd}')\n";
}
private static IReadOnlyList<float[]> ParseAndValidateVectors(string output, int expectedCount)
{
var json = ExtractJson(output);
float[][]? vectors;
try
{
vectors = JsonSerializer.Deserialize<float[][]>(json);
}
catch (JsonException exception)
{
throw new InvalidDataException("Resemblyzer returned malformed vector JSON.", exception);
}
if (vectors is null || vectors.Length != expectedCount)
{
throw new InvalidDataException(
$"Resemblyzer returned {vectors?.Length ?? 0} vectors for {expectedCount} WAV samples.");
}
return vectors
.Select((vector, index) => SpeakerVoiceVectors.Normalize(vector, $"Resemblyzer vector {index}"))
.ToList();
}
private static string ExtractJson(string output)
{
var start = output.IndexOf(JsonStart, StringComparison.Ordinal);
if (start < 0)
{
throw new InvalidDataException("Resemblyzer output did not contain the JSON start marker.");
}
start += JsonStart.Length;
var end = output.IndexOf(JsonEnd, start, StringComparison.Ordinal);
if (end < 0)
{
throw new InvalidDataException("Resemblyzer output did not contain the JSON end marker.");
}
return output[start..end].Trim();
}
private string BuildEnvironmentKey()
{
var settings = string.Join('\n', EnvironmentManifest);
var hash = SHA256.HashData(Encoding.UTF8.GetBytes(settings));
return Convert.ToHexString(hash)[..16].ToLowerInvariant();
}
private string TorchRequirement => $"torch=={options.TorchVersion}";
private string ResemblyzerRequirement => $"Resemblyzer=={options.PackageVersion}";
private static string[] WarmupArguments =>
[
"-c",
"from resemblyzer import VoiceEncoder; VoiceEncoder('cpu', verbose=False); print('Resemblyzer warm-up complete')"
];
private string[] RuntimeDependencyRequirements =>
[
NumpyBeforePython313Requirement,
NumpyFromPython313Requirement,
LibrosaRequirement,
ScipyRequirement,
$"webrtcvad-wheels=={options.WebRtcVadVersion}"
];
private IEnumerable<string> EnvironmentManifest =>
[
EnvironmentSchemaVersion,
options.PythonCommand,
options.TorchIndexUrl,
TorchRequirement,
.. RuntimeDependencyRequirements,
ResemblyzerRequirement
];
private static string GetEnvironmentPythonPath(string environmentFolder)
{
return OperatingSystem.IsWindows()
? Path.Combine(environmentFolder, "Scripts", "python.exe")
: Path.Combine(environmentFolder, "bin", "python");
}
private void ValidateDependencySettings()
{
if (string.IsNullOrWhiteSpace(options.PythonCommand))
{
throw new InvalidOperationException("The Resemblyzer Python command cannot be empty.");
}
ValidateVersion(options.PackageVersion, "Resemblyzer package");
ValidateVersion(options.TorchVersion, "PyTorch");
ValidateVersion(options.WebRtcVadVersion, "webrtcvad-wheels");
if (!Uri.TryCreate(options.TorchIndexUrl, UriKind.Absolute, out var indexUri)
|| indexUri.Scheme != Uri.UriSchemeHttps)
{
throw new InvalidOperationException(
$"Invalid Resemblyzer PyTorch index URL '{options.TorchIndexUrl}'.");
}
}
private static void ValidateVersion(string version, string dependency)
{
if (!PackageVersionPattern().IsMatch(version))
{
throw new InvalidOperationException($"Invalid {dependency} version '{version}'.");
}
}
private async Task<T> RunWithTimeoutAsync<T>(
Func<CancellationToken, Task<T>> operation,
CancellationToken cancellationToken)
{
using var timeoutSource = options.CommandTimeout > TimeSpan.Zero
? new CancellationTokenSource(options.CommandTimeout)
: null;
using var linkedSource = timeoutSource is null
? null
: CancellationTokenSource.CreateLinkedTokenSource(cancellationToken, timeoutSource.Token);
try
{
return await operation(linkedSource?.Token ?? cancellationToken);
}
catch (OperationCanceledException) when (
!cancellationToken.IsCancellationRequested && timeoutSource?.IsCancellationRequested == true)
{
throw new TimeoutException(
$"Resemblyzer command timed out after {options.CommandTimeout.ToString(null, CultureInfo.InvariantCulture)}.");
}
}
private static void ThrowIfFailed(CommandResult result, string operation)
{
if (result.ExitCode != 0)
{
throw new InvalidOperationException(
$"Resemblyzer {operation} failed with exit code {result.ExitCode}: {result.StandardError}");
}
}
[GeneratedRegex("^[0-9A-Za-z.+-]+$", RegexOptions.CultureInvariant)]
private static partial Regex PackageVersionPattern();
}