@huggingface/tasks - npm Package Compare versions

Comparing version 0.10.11 to 0.10.12

dist/src/index.d.ts

@@ -19,2 +19,4 @@ export { LIBRARY_TASK_MAPPING } from "./library-to-tasks";
 export type { LocalApp, LocalAppKey } from "./local-apps";
+export { DATASET_LIBRARIES_UI_ELEMENTS } from "./dataset-libraries";
+export type { DatasetLibraryUiElement, DatasetLibraryKey } from "./dataset-libraries";
 //# sourceMappingURL=index.d.ts.map

dist/src/local-apps.d.ts

@@ -87,2 +87,24 @@ import type { ModelData } from "./model-data";
     };
+    jellybox: {
+        prettyLabel: string;
+        docsUrl: string;
+        mainTask: "text-generation";
+        displayOnModelPage: (model: ModelData) => boolean;
+        deeplink: (model: ModelData) => URL;
+    };
+    msty: {
+        prettyLabel: string;
+        docsUrl: string;
+        mainTask: "text-generation";
+        displayOnModelPage: typeof isGgufModel;
+        deeplink: (model: ModelData) => URL;
+    };
+    recursechat: {
+        prettyLabel: string;
+        docsUrl: string;
+        mainTask: "text-generation";
+        macOSOnly: true;
+        displayOnModelPage: typeof isGgufModel;
+        deeplink: (model: ModelData) => URL;
+    };
     drawthings: {
@@ -89,0 +111,0 @@ prettyLabel: string;

dist/src/model-libraries-snippets.d.ts

@@ -22,2 +22,3 @@ import type { ModelData } from "./model-data";
 export declare const sklearn: (model: ModelData) => string[];
+export declare const stable_audio_tools: (model: ModelData) => string[];
 export declare const fastai: (model: ModelData) => string[];
@@ -39,2 +40,3 @@ export declare const sampleFactory: (model: ModelData) => string[];
 export declare const voicecraft: (model: ModelData) => string[];
+export declare const chattts: () => string[];
 export declare const mlx: (model: ModelData) => string[];
@@ -41,0 +43,0 @@ export declare const mlxim: (model: ModelData) => string[];

dist/src/model-libraries.d.ts

@@ -116,2 +116,14 @@ import type { ModelData } from "./model-data";
     };
+    chat_tts: {
+        prettyLabel: string;
+        repoName: string;
+        repoUrl: string;
+        filter: false;
+        countDownloads: {
+            term: {
+                path: string;
+            };
+        };
+        snippets: () => string[];
+    };
     diffusers: {
@@ -170,2 +182,7 @@ prettyLabel: string;
         filter: true;
+        countDownloads: {
+            wildcard: {
+                path: string;
+            };
+        };
     };
@@ -409,2 +426,14 @@ flair: {
     };
+    "stable-audio-tools": {
+        prettyLabel: string;
+        repoName: string;
+        repoUrl: string;
+        filter: false;
+        countDownloads: {
+            term: {
+                path: string;
+            };
+        };
+        snippets: (model: ModelData) => string[];
+    };
     "stable-baselines3": {
@@ -513,4 +542,4 @@ prettyLabel: string;
 export type ModelLibraryKey = keyof typeof MODEL_LIBRARIES_UI_ELEMENTS;
-export declare const ALL_MODEL_LIBRARY_KEYS: ("adapter-transformers" | "allennlp" | "asteroid" | "audiocraft" | "bertopic" | "big_vision" | "diffusers" | "doctr" | "elm" | "espnet" | "fairseq" | "fastai" | "fasttext" | "flair" | "gliner" | "grok" | "keras" | "keras-nlp" | "k2" | "mindspore" | "ml-agents" | "mlx" | "mlx-image" | "nemo" | "open_clip" | "paddlenlp" | "peft" | "pyannote-audio" | "pythae" | "sample-factory" | "sentence-transformers" | "setfit" | "sklearn" | "spacy" | "span-marker" | "speechbrain" | "stable-baselines3" | "stanza" | "tensorflowtts" | "timesfm" | "timm" | "transformers" | "transformers.js" | "unity-sentis" | "voicecraft" | "whisperkit")[];
-export declare const ALL_DISPLAY_MODEL_LIBRARY_KEYS: ("adapter-transformers" | "allennlp" | "asteroid" | "audiocraft" | "bertopic" | "big_vision" | "diffusers" | "doctr" | "elm" | "espnet" | "fairseq" | "fastai" | "fasttext" | "flair" | "gliner" | "grok" | "keras" | "keras-nlp" | "k2" | "mindspore" | "ml-agents" | "mlx" | "mlx-image" | "nemo" | "open_clip" | "paddlenlp" | "peft" | "pyannote-audio" | "pythae" | "sample-factory" | "sentence-transformers" | "setfit" | "sklearn" | "spacy" | "span-marker" | "speechbrain" | "stable-baselines3" | "stanza" | "tensorflowtts" | "timesfm" | "timm" | "transformers" | "transformers.js" | "unity-sentis" | "voicecraft" | "whisperkit")[];
+export declare const ALL_MODEL_LIBRARY_KEYS: ("adapter-transformers" | "allennlp" | "asteroid" | "audiocraft" | "bertopic" | "big_vision" | "chat_tts" | "diffusers" | "doctr" | "elm" | "espnet" | "fairseq" | "fastai" | "fasttext" | "flair" | "gliner" | "grok" | "keras" | "keras-nlp" | "k2" | "mindspore" | "ml-agents" | "mlx" | "mlx-image" | "nemo" | "open_clip" | "paddlenlp" | "peft" | "pyannote-audio" | "pythae" | "sample-factory" | "sentence-transformers" | "setfit" | "sklearn" | "spacy" | "span-marker" | "speechbrain" | "stable-audio-tools" | "stable-baselines3" | "stanza" | "tensorflowtts" | "timesfm" | "timm" | "transformers" | "transformers.js" | "unity-sentis" | "voicecraft" | "whisperkit")[];
+export declare const ALL_DISPLAY_MODEL_LIBRARY_KEYS: ("adapter-transformers" | "allennlp" | "asteroid" | "audiocraft" | "bertopic" | "big_vision" | "chat_tts" | "diffusers" | "doctr" | "elm" | "espnet" | "fairseq" | "fastai" | "fasttext" | "flair" | "gliner" | "grok" | "keras" | "keras-nlp" | "k2" | "mindspore" | "ml-agents" | "mlx" | "mlx-image" | "nemo" | "open_clip" | "paddlenlp" | "peft" | "pyannote-audio" | "pythae" | "sample-factory" | "sentence-transformers" | "setfit" | "sklearn" | "spacy" | "span-marker" | "speechbrain" | "stable-audio-tools" | "stable-baselines3" | "stanza" | "tensorflowtts" | "timesfm" | "timm" | "transformers" | "transformers.js" | "unity-sentis" | "voicecraft" | "whisperkit")[];
 //# sourceMappingURL=model-libraries.d.ts.map

package.json

 {
   "name": "@huggingface/tasks",
   "packageManager": "pnpm@8.10.5",
-  "version": "0.10.11",
+  "version": "0.10.12",
   "description": "List of ML tasks for huggingface.co/tasks",
@@ -6,0 +6,0 @@ "repository": "https://github.com/huggingface/huggingface.js.git",

src/index.ts

@@ -52,1 +52,4 @@ export { LIBRARY_TASK_MAPPING } from "./library-to-tasks";
 export type { LocalApp, LocalAppKey } from "./local-apps";
+
+export { DATASET_LIBRARIES_UI_ELEMENTS } from "./dataset-libraries";
+export type { DatasetLibraryUiElement, DatasetLibraryKey } from "./dataset-libraries";

src/local-apps.ts

@@ -121,2 +121,36 @@ import type { ModelData } from "./model-data";
 	},
+	jellybox: {
+		prettyLabel: "Jellybox",
+		docsUrl: "https://jellybox.com",
+		mainTask: "text-generation",
+		displayOnModelPage: (model) =>
+			isGgufModel(model) ||
+			(model.library_name === "diffusers" &&
+				model.tags.includes("safetensors") &&
+				(model.pipeline_tag === "text-to-image" || model.tags.includes("lora"))),
+		deeplink: (model) => {
+			if (isGgufModel(model)) {
+				return new URL(`jellybox://llm/models/huggingface/LLM/${model.id}`);
+			} else if (model.tags.includes("lora")) {
+				return new URL(`jellybox://image/models/huggingface/ImageLora/${model.id}`);
+			} else {
+				return new URL(`jellybox://image/models/huggingface/Image/${model.id}`);
+			}
+		},
+	},
+	msty: {
+		prettyLabel: "Msty",
+		docsUrl: "https://msty.app",
+		mainTask: "text-generation",
+		displayOnModelPage: isGgufModel,
+		deeplink: (model) => new URL(`msty://models/search/hf/${model.id}`),
+	},
+	recursechat: {
+		prettyLabel: "RecurseChat",
+		docsUrl: "https://recurse.chat",
+		mainTask: "text-generation",
+		macOSOnly: true,
+		displayOnModelPage: isGgufModel,
+		deeplink: (model) => new URL(`recursechat://new-hf-gguf-model?hf-model-id=${model.id}`),
+	},
 	drawthings: {
@@ -123,0 +157,0 @@ prettyLabel: "Draw Things",

src/model-libraries-snippets.ts

@@ -329,2 +329,39 @@ import type { ModelData } from "./model-data";
 
+export const stable_audio_tools = (model: ModelData): string[] => [
+	`import torch
+import torchaudio
+from einops import rearrange
+from stable_audio_tools import get_pretrained_model
+from stable_audio_tools.inference.generation import generate_diffusion_cond
+
+device = "cuda" if torch.cuda.is_available() else "cpu"
+
+# Download model
+model, model_config = get_pretrained_model("${model.id}")
+sample_rate = model_config["sample_rate"]
+sample_size = model_config["sample_size"]
+
+model = model.to(device)
+
+# Set up text and timing conditioning
+conditioning = [{
+	"prompt": "128 BPM tech house drum loop",
+}]
+
+# Generate stereo audio
+output = generate_diffusion_cond(
+	model,
+	conditioning=conditioning,
+	sample_size=sample_size,
+	device=device
+)
+
+# Rearrange audio batch to a single sequence
+output = rearrange(output, "b d n -> d (b n)")
+
+# Peak normalize, clip, convert to int16, and save to file
+output = output.to(torch.float32).div(torch.max(torch.abs(output))).clamp(-1, 1).mul(32767).to(torch.int16).cpu()
+torchaudio.save("output.wav", output, sample_rate)`,
+];
+
 export const fastai = (model: ModelData): string[] => [
@@ -557,2 +594,16 @@ `from huggingface_hub import from_pretrained_fastai
 
+export const chattts = (): string[] => [
+	`import ChatTTS
+import torchaudio
+
+chat = ChatTTS.Chat()
+chat.load_models(compile=False) # Set to True for better performance
+
+texts = ["PUT YOUR TEXT HERE",]
+
+wavs = chat.infer(texts, )
+
+torchaudio.save("output1.wav", torch.from_numpy(wavs[0]), 24000)`,
+];
+
 export const mlx = (model: ModelData): string[] => [
@@ -559,0 +610,0 @@ `pip install huggingface_hub hf_transfer

src/model-libraries.ts

@@ -114,2 +114,10 @@ import * as snippets from "./model-libraries-snippets";
 	},
+	chat_tts: {
+		prettyLabel: "ChatTTS",
+		repoName: "ChatTTS",
+		repoUrl: "https://github.com/2noise/ChatTTS.git",
+		filter: false,
+		countDownloads: { term: { path: "asset/GPT.pt" } },
+		snippets: snippets.chattts,
+	},
 	diffusers: {
@@ -167,2 +175,5 @@ prettyLabel: "Diffusers",
 		filter: true,
+		countDownloads: {
+			wildcard: { path: "*.bin" },
+		},
 	},
@@ -366,2 +377,10 @@ flair: {
 	},
+	"stable-audio-tools": {
+		prettyLabel: "Stable Audio Tools",
+		repoName: "stable-audio-tools",
+		repoUrl: "https://github.com/Stability-AI/stable-audio-tools.git",
+		filter: false,
+		countDownloads: { term: { path: "model.safetensors" } },
+		snippets: snippets.stable_audio_tools,
+	},
 	"stable-baselines3": {
@@ -368,0 +387,0 @@ prettyLabel: "stable-baselines3",

src/tasks/automatic-speech-recognition/about.md

@@ -39,3 +39,3 @@ ## Use Cases
 
-You can also use[huggingface.js](https://github.com/huggingface/huggingface.js), the JavaScript client, to transcribe models with the Inference API.
+You can also use [huggingface.js](https://github.com/huggingface/huggingface.js), the JavaScript client, to transcribe audio with the Serverless Inference API.
 
@@ -52,3 +52,3 @@ ```javascript
 
-For transformers compatible models like Whisper, Wav2Vec2, HuBERT, etc. You can also run inference in Python using transformers as follows:
+For transformers-compatible models like Whisper, Wav2Vec2, and HuBERT, you can also run inference with the library as follows:
 
@@ -55,0 +55,0 @@ ```python

No alert changes

Improved metrics

Total package byte prevSize

1176908

increased by1.47%

Number of package files

360

increased by0.84%

Lines of code

28873

increased by1.78%

No dependency changes