| """ |
| Community fork of MariaK/Check-my-progress-Audio-Course. |
| |
| Fixes the upstream RUNTIME_ERROR: the original calls certification() eagerly at |
| module load AND the Unit 7 ("demo") branch downloads usernames.csv from the |
| `huggingface-course/audio-course-u7-hands-on` dataset, which has been deleted |
| (404) — with no try/except, so the Space crashed on startup. |
| |
| Changes (behaviour-preserving for Units 4/5/6): |
| 1. Do NOT run certification() at import time (the table starts empty). |
| 2. Guard the Unit 7 download so a deleted/gated dataset no longer crashes the |
| app; Unit 7 is reported as "auto-check unavailable" instead. |
| 3. Handle an empty/blank username gracefully. |
| |
| Units 4/5/6 are verified exactly as upstream (against your models on the Hub). |
| """ |
|
|
| import os |
| import re |
|
|
| import gradio as gr |
| import pandas as pd |
| import requests |
| from huggingface_hub import HfApi, ModelCard, hf_hub_download |
| from huggingface_hub.repocard import metadata_load |
|
|
|
|
| def pass_emoji(passed): |
| return "✅" if passed is True else "❌" |
|
|
|
|
| api = HfApi() |
| USERNAMES_DATASET_ID = "huggingface-course/audio-course-u7-hands-on" |
| HF_TOKEN = os.environ.get("HF_TOKEN") |
|
|
|
|
| def get_user_models(hf_username, task): |
| models = api.list_models(author=hf_username, filter=[task]) |
| user_model_ids = [x.modelId for x in models] |
|
|
| match task: |
| case "audio-classification": |
| dataset = "marsyas/gtzan" |
| case "automatic-speech-recognition": |
| dataset = "PolyAI/minds14" |
| case "text-to-speech": |
| dataset = "" |
| case _: |
| print("Unsupported task") |
| dataset = "" |
|
|
| if dataset == "": |
| return user_model_ids |
|
|
| dataset_specific_models = [] |
| for model in user_model_ids: |
| meta = get_metadata(model) |
| if meta is None: |
| continue |
| try: |
| if meta["datasets"] == [dataset]: |
| dataset_specific_models.append(model) |
| except Exception: |
| continue |
| return dataset_specific_models |
|
|
|
|
| def calculate_best_result(user_models, task): |
| best_model = "" |
| if task == "audio-classification": |
| best_result = -100 |
| larger_is_better = True |
| elif task == "automatic-speech-recognition": |
| best_result = 100 |
| larger_is_better = False |
|
|
| for model in user_models: |
| meta = get_metadata(model) |
| if meta is None: |
| continue |
| metric = parse_metrics(model, task) |
| if metric is None: |
| continue |
| if larger_is_better: |
| if metric > best_result: |
| best_result = metric |
| best_model = meta["model-index"][0]["name"] |
| else: |
| if metric < best_result: |
| best_result = metric |
| best_model = meta["model-index"][0]["name"] |
| return best_result, best_model |
|
|
|
|
| def get_metadata(model_id): |
| try: |
| readme_path = hf_hub_download(model_id, filename="README.md") |
| return metadata_load(readme_path) |
| except requests.exceptions.HTTPError: |
| return None |
|
|
|
|
| def extract_metric(model_card_content, task): |
| accuracy_pattern = r"(?:Accuracy|eval_accuracy): (\d+\.\d+)" |
| wer_pattern = r"Wer: (\d+\.\d+)" |
| pattern = accuracy_pattern if task == "audio-classification" else wer_pattern |
| match = re.search(pattern, model_card_content) |
| return float(match.group(1)) if match else None |
|
|
|
|
| def parse_metrics(model, task): |
| card = ModelCard.load(model) |
| return extract_metric(card.content, task) |
|
|
|
|
| def certification(hf_username): |
| hf_username = (hf_username or "").strip() |
| results_certification = [ |
| { |
| "unit": "Unit 4: Audio Classification", |
| "task": "audio-classification", |
| "baseline_metric": 0.87, |
| "best_result": 0, |
| "best_model_id": "", |
| "passed_": False, |
| }, |
| { |
| "unit": "Unit 5: Automatic Speech Recognition", |
| "task": "automatic-speech-recognition", |
| "baseline_metric": 0.37, |
| "best_result": 0, |
| "best_model_id": "", |
| "passed_": False, |
| }, |
| { |
| "unit": "Unit 6: Text-to-Speech", |
| "task": "text-to-speech", |
| "baseline_metric": 0, |
| "best_result": 0, |
| "best_model_id": "", |
| "passed_": False, |
| }, |
| { |
| "unit": "Unit 7: Audio applications", |
| "task": "demo", |
| "baseline_metric": 0, |
| "best_result": 0, |
| "best_model_id": "", |
| "passed_": False, |
| }, |
| ] |
|
|
| for unit in results_certification: |
| unit["passed"] = pass_emoji(unit["passed_"]) |
| if not hf_username: |
| continue |
|
|
| match unit["task"]: |
| case "audio-classification": |
| try: |
| m = get_user_models(hf_username, task="audio-classification") |
| best_result, best_model_id = calculate_best_result( |
| m, task="audio-classification" |
| ) |
| unit["best_result"] = best_result |
| unit["best_model_id"] = best_model_id |
| if unit["best_result"] >= unit["baseline_metric"]: |
| unit["passed_"] = True |
| unit["passed"] = pass_emoji(unit["passed_"]) |
| except Exception: |
| print("No relevant models / metrics for audio classification") |
| case "automatic-speech-recognition": |
| try: |
| m = get_user_models( |
| hf_username, task="automatic-speech-recognition" |
| ) |
| best_result, best_model_id = calculate_best_result( |
| m, task="automatic-speech-recognition" |
| ) |
| unit["best_result"] = best_result |
| unit["best_model_id"] = best_model_id |
| if unit["best_result"] <= unit["baseline_metric"]: |
| unit["passed_"] = True |
| unit["passed"] = pass_emoji(unit["passed_"]) |
| except Exception: |
| print("No relevant models / metrics for ASR") |
| case "text-to-speech": |
| try: |
| m = get_user_models(hf_username, task="text-to-speech") |
| if m: |
| unit["best_result"] = 0 |
| unit["best_model_id"] = m[0] |
| unit["passed_"] = True |
| unit["passed"] = pass_emoji(unit["passed_"]) |
| except Exception: |
| print("No relevant models for TTS") |
| case "demo": |
| |
| try: |
| path = hf_hub_download( |
| USERNAMES_DATASET_ID, |
| repo_type="dataset", |
| filename="usernames.csv", |
| token=HF_TOKEN, |
| ) |
| users = pd.read_csv(path) |
| if hf_username in users["username"].tolist(): |
| unit["best_result"] = 0 |
| unit["best_model_id"] = "Demo check passed" |
| unit["passed_"] = True |
| unit["passed"] = pass_emoji(unit["passed_"]) |
| except Exception: |
| unit["best_model_id"] = ( |
| "Unit 7 auto-check unavailable — upstream usernames dataset " |
| "deleted; verify your public demo via the Unit 7 assessment space" |
| ) |
| case _: |
| print("Unknown task") |
|
|
| df = pd.DataFrame(results_certification) |
| return df[ |
| ["passed", "unit", "task", "baseline_metric", "best_result", "best_model_id"] |
| ] |
|
|
|
|
| with gr.Blocks() as demo: |
| gr.Markdown( |
| """ |
| # 🏆 Check your progress in the Audio Course (community fork) 🏆 |
| |
| > Fork of `MariaK/Check-my-progress-Audio-Course` that fixes the upstream |
| > startup crash (the Unit 7 check downloaded a now-deleted dataset). Units |
| > 4/5/6 are verified exactly as in the original, against your models on the Hub. |
| |
| - Certificate of completion: **pass 3 of 4** assignments. |
| - Honors certificate: **pass 4 of 4**. |
| |
| Your trained-model metric must be equal to or better than the baseline. |
| Unit 7's automatic check is unavailable upstream (deleted dataset); use the |
| [Unit 7 assessment space](https://huggingface.co/spaces/huggingface-course/audio-course-u7-assessment) |
| (or a working fork) to confirm your public demo. |
| |
| Enter your Hugging Face username to check your progress: |
| """ |
| ) |
| hf_username = gr.Textbox( |
| placeholder="VoicesColeby", label="Your Hugging Face Username" |
| ) |
| check_progress_button = gr.Button(value="Check my progress") |
| output = gr.components.Dataframe(value=None) |
| check_progress_button.click(fn=certification, inputs=hf_username, outputs=output) |
|
|
| demo.launch() |
|
|
