Fix AN4 dataset links (#6926)

* Fix an4 dataset link in docs Signed-off-by: Vladimir Bataev <[email protected]> * Remove broken a4 dataset links from tutorials Signed-off-by: Vladimir Bataev <[email protected]> --------- Signed-off-by: Vladimir Bataev <[email protected]>
NVIDIA · Jun 28, 2023 · 69747d8 · 69747d8
1 parent 3b4f37a
commit 69747d8
Show file tree

Hide file tree

Showing 8 changed files with 8 additions and 8 deletions.
diff --git a/docs/source/asr/datasets.rst b/docs/source/asr/datasets.rst
@@ -126,7 +126,7 @@ AN4 Dataset
 This is a small dataset recorded and distributed by Carnegie Mellon University. It consists of recordings of people spelling out
 addresses, names, etc. Information about this dataset can be found on the `official CMU site <http://www.speech.cs.cmu.edu/databases/an4/>`_.
 
-#. `Download and extract the dataset <http://www.speech.cs.cmu.edu/databases/an4/an4_sphere.tar.gz>`_ (which is labeled "NIST's Sphere audio (.sph) format (64M)".
+#. `Download and extract the dataset <https://dldata-public.s3.us-east-2.amazonaws.com/an4_sphere.tar.gz>`_ (which is labeled "NIST's Sphere audio (.sph) format (64M)".
 
 #. Convert the ``.sph`` files to ``.wav`` using sox, and build one training and one test manifest.
 

diff --git a/tutorials/asr/ASR_for_telephony_speech.ipynb b/tutorials/asr/ASR_for_telephony_speech.ipynb
@@ -103,7 +103,7 @@
                 "# Download the dataset. This will take a few moments...\n",
                 "print(\"******\")\n",
                 "if not os.path.exists(data_dir + '/an4_sphere.tar.gz'):\n",
-                "    an4_url = 'https://dldata-public.s3.us-east-2.amazonaws.com/an4_sphere.tar.gz'  # for the original source, please visit http://www.speech.cs.cmu.edu/databases/an4/an4_sphere.tar.gz \n",
+                "    an4_url = 'https://dldata-public.s3.us-east-2.amazonaws.com/an4_sphere.tar.gz'\n",
                 "    an4_path = wget.download(an4_url, data_dir)\n",
                 "    print(f\"Dataset downloaded at: {an4_path}\")\n",
                 "else:\n",

diff --git a/tutorials/asr/ASR_with_NeMo.ipynb b/tutorials/asr/ASR_with_NeMo.ipynb
@@ -189,7 +189,7 @@
                 "# Download the dataset. This will take a few moments...\n",
                 "print(\"******\")\n",
                 "if not os.path.exists(data_dir + '/an4_sphere.tar.gz'):\n",
-                "    an4_url = 'https://dldata-public.s3.us-east-2.amazonaws.com/an4_sphere.tar.gz'  # for the original source, please visit http://www.speech.cs.cmu.edu/databases/an4/an4_sphere.tar.gz \n",
+                "    an4_url = 'https://dldata-public.s3.us-east-2.amazonaws.com/an4_sphere.tar.gz'\n",
                 "    an4_path = wget.download(an4_url, data_dir)\n",
                 "    print(f\"Dataset downloaded at: {an4_path}\")\n",
                 "else:\n",

diff --git a/tutorials/asr/ASR_with_Subword_Tokenization.ipynb b/tutorials/asr/ASR_with_Subword_Tokenization.ipynb
@@ -372,7 +372,7 @@
         "# Download the dataset. This will take a few moments...\r\n",
         "print(\"******\")\r\n",
         "if not os.path.exists(data_dir + '/an4_sphere.tar.gz'):\r\n",
-        "    an4_url = 'https://dldata-public.s3.us-east-2.amazonaws.com/an4_sphere.tar.gz'  # for the original source, please visit http://www.speech.cs.cmu.edu/databases/an4/an4_sphere.tar.gz \r\n",
+        "    an4_url = 'https://dldata-public.s3.us-east-2.amazonaws.com/an4_sphere.tar.gz'\r\n",
         "    an4_path = wget.download(an4_url, data_dir)\r\n",
         "    print(f\"Dataset downloaded at: {an4_path}\")\r\n",
         "else:\r\n",

diff --git a/tutorials/asr/ASR_with_Transducers.ipynb b/tutorials/asr/ASR_with_Transducers.ipynb
@@ -137,7 +137,7 @@
         "# Download the dataset. This will take a few moments...\n",
         "print(\"******\")\n",
         "if not os.path.exists(data_dir + '/an4_sphere.tar.gz'):\n",
-        "    an4_url = 'https://dldata-public.s3.us-east-2.amazonaws.com/an4_sphere.tar.gz'  # for the original source, please visit http://www.speech.cs.cmu.edu/databases/an4/an4_sphere.tar.gz \n",
+        "    an4_url = 'https://dldata-public.s3.us-east-2.amazonaws.com/an4_sphere.tar.gz'\n",
         "    an4_path = wget.download(an4_url, data_dir)\n",
         "    print(f\"Dataset downloaded at: {an4_path}\")\n",
         "else:\n",

diff --git a/tutorials/asr/Online_Noise_Augmentation.ipynb b/tutorials/asr/Online_Noise_Augmentation.ipynb
@@ -135,7 +135,7 @@
                 "# Download the dataset. This will take a few moments...\n",
                 "print(\"******\")\n",
                 "if not os.path.exists(data_dir + '/an4_sphere.tar.gz'):\n",
-                "    an4_url = 'https://dldata-public.s3.us-east-2.amazonaws.com/an4_sphere.tar.gz'  # for the original source, please visit http://www.speech.cs.cmu.edu/databases/an4/an4_sphere.tar.gz \n",
+                "    an4_url = 'https://dldata-public.s3.us-east-2.amazonaws.com/an4_sphere.tar.gz'\n",
                 "    an4_path = wget.download(an4_url, data_dir)\n",
                 "    print(f\"Dataset downloaded at: {an4_path}\")\n",
                 "else:\n",

diff --git a/tutorials/asr/asr_adapters/ASR_with_Adapters.ipynb b/tutorials/asr/asr_adapters/ASR_with_Adapters.ipynb
@@ -190,7 +190,7 @@
         "# Download the dataset. This will take a few moments...\n",
         "print(\"******\")\n",
         "if not os.path.exists(data_dir + '/an4_sphere.tar.gz'):\n",
-        "    an4_url = 'https://dldata-public.s3.us-east-2.amazonaws.com/an4_sphere.tar.gz'  # for the original source, please visit http://www.speech.cs.cmu.edu/databases/an4/an4_sphere.tar.gz \n",
+        "    an4_url = 'https://dldata-public.s3.us-east-2.amazonaws.com/an4_sphere.tar.gz'\n",
         "    an4_path = wget.download(an4_url, data_dir)\n",
         "    print(f\"Dataset downloaded at: {an4_path}\")\n",
         "else:\n",

diff --git a/tutorials/speaker_tasks/Speaker_Identification_Verification.ipynb b/tutorials/speaker_tasks/Speaker_Identification_Verification.ipynb
@@ -85,7 +85,7 @@
     "# Download the dataset. This will take a few moments...\n",
     "print(\"******\")\n",
     "if not os.path.exists(data_dir + '/an4_sphere.tar.gz'):\n",
-    "    an4_url = 'https://dldata-public.s3.us-east-2.amazonaws.com/an4_sphere.tar.gz'  # for the original source, please visit http://www.speech.cs.cmu.edu/databases/an4/an4_sphere.tar.gz \n",
+    "    an4_url = 'https://dldata-public.s3.us-east-2.amazonaws.com/an4_sphere.tar.gz'\n",
     "    an4_path = wget.download(an4_url, data_dir)\n",
     "    print(f\"Dataset downloaded at: {an4_path}\")\n",
     "else:\n",