C#からHugging Faceモデルを呼ぶ：DotNetPy 0.6.0でWhisper・sentence-transformers・Stable Diffusionを動かす

using DotNetPy;
using DotNetPy.Uv;

using var project = PythonProject.CreateBuilder()
    .WithProjectName("dotnetpy-ml-embeddings")
    .WithPythonVersion("==3.12.*")
    .AddDependencies(
        "sentence-transformers==2.7.0",
        "transformers==4.40.2",
        "torch>=2.2,<2.5")
    .Build();

await project.InitializeAsync();
var executor = project.GetExecutor();

executor.Execute(@"
import numpy as np
from sentence_transformers import SentenceTransformer
model = SentenceTransformer('all-MiniLM-L6-v2')
");

var corpus = new[]
{
    "Python is a popular programming language for data science.",
    "C# and .NET are great for building enterprise applications.",
    "Rust offers memory safety without garbage collection.",
    "Pizza is delicious with various toppings.",
    // …
};
var query = "Tell me about programming languages";

using var hits = executor.ExecuteAndCapture(@"
corpus_emb = model.encode(corpus, normalize_embeddings=True)
query_emb = model.encode([query], normalize_embeddings=True)[0]
sims = corpus_emb @ query_emb
top_idx = np.argsort(-sims)[:3]
result = [
    {'rank': int(rank + 1), 'score': float(sims[i]), 'text': corpus[int(i)]}
    for rank, i in enumerate(top_idx)
]
", new Dictionary<string, object?> { { "corpus", corpus }, { "query", query } });

foreach (var hit in hits!.RootElement.EnumerateArray())
{
    Console.WriteLine($"  {hit.GetProperty("rank").GetInt32()}. " +
                      $"[{hit.GetProperty("score").GetDouble():F3}] " +
                      $"{hit.GetProperty("text").GetString()}");
}

  1. [0.578] Python is a popular programming language for data science.
  2. [0.370] C# and .NET are great for building enterprise applications.
  3. [0.203] Rust offers memory safety without garbage collection.

var executor = project.GetExecutor();
executor.Execute(@"
from transformers import pipeline
import torch
asr = pipeline(
    'automatic-speech-recognition',
    model='openai/whisper-base.en',
    chunk_length_s=30,
    return_timestamps=True,
    torch_dtype=torch.float32,
)
");

using var transcript = executor.ExecuteAndCapture(@"
out = asr(audio_path)
chunks = [
    {'start': float(c['timestamp'][0]), 'end': float(c['timestamp'][1]),
     'text': c['text'].strip()}
    for c in out.get('chunks', [])
    if c['timestamp'][0] is not None and c['timestamp'][1] is not None
]
result = {'text': out['text'].strip(), 'chunks': chunks}
", new Dictionary<string, object?> { { "audio_path", audioPath } });

Console.WriteLine($"\"{transcript!.GetString("text")}\"");
foreach (var c in transcript.RootElement.GetProperty("chunks").EnumerateArray())
    Console.WriteLine($"  [{c.GetProperty("start").GetDouble():F2}s → " +
                      $"{c.GetProperty("end").GetDouble():F2}s] " +
                      $"{c.GetProperty("text").GetString()}");

"And so my fellow Americans, ask not what your country can do for you,
 ask what you can do for your country."

  [0.00s → 11.00s] And so my fellow Americans, ask not what your country can
                   do for you, ask what you can do for your country.

executor.Execute(@"
import torch
from diffusers import AutoPipelineForText2Image
pipe = AutoPipelineForText2Image.from_pretrained(
    'stabilityai/sd-turbo',
    torch_dtype=torch.float32,
    safety_checker=None, requires_safety_checker=False,
)
pipe.set_progress_bar_config(disable=True)
");

using var meta = executor.ExecuteAndCapture(@"
import time, os
t0 = time.time()
img = pipe(prompt=prompt, num_inference_steps=1, guidance_scale=0.0).images[0]
elapsed = time.time() - t0
out_path = os.path.join(out_dir, 'generated.png')
img.save(out_path)
result = {
    'path': out_path,
    'width': img.size[0],
    'height': img.size[1],
    'size_bytes': os.path.getsize(out_path),
    'elapsed_seconds': elapsed,
}
", new Dictionary<string, object?>
{
    { "prompt", "a serene mountain lake at sunset, oil painting style" },
    { "out_dir", outDir },
});

Console.WriteLine($"  Saved:   {meta!.GetString("path")}");
Console.WriteLine($"  Size:    {meta.GetInt32("width")}×{meta.GetInt32("height")} px, " +
                  $"{meta.GetInt32("size_bytes"):N0} bytes");
Console.WriteLine($"  Inference: {meta.GetDouble("elapsed_seconds"):F2}s");

  Saved:   .../samples/ml-image-gen/output/generated.png
  Size:    512×512 px, 434,242 bytes
  Inference: 31.19s

dotnet add package DotNetPy --version 0.6.0

using var project = PythonProject.CreateBuilder()
    .WithProjectName("my-app")
    .WithPythonVersion("==3.12.*")
    .AddDependencies("transformers==4.40.2", "torch>=2.2,<2.5")
    .Build();

await project.InitializeAsync();

using var iso = Python.CreateIsolated();
iso.Execute("import json");
iso.Execute("data = {'k': 1}");   // `data` はこの実行器だけが見えます

Parallel.For(0, Environment.ProcessorCount, threadId =>
{
    using var iso = Python.CreateIsolated();
    iso.Execute("import torch; from transformers import pipeline");
    iso.Execute(@"
asr = pipeline('automatic-speech-recognition',
               model='openai/whisper-base.en')
");
    using var r = iso.ExecuteAndCapture(@"
out = asr(audio_path)
result = {'text': out['text']}
", new Dictionary<string, object?> { { "audio_path", path } });

    Console.WriteLine(r?.GetString("text"));
});