Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Update notebook #2391

Merged
merged 1 commit into from
Jun 23, 2021
Merged

Update notebook #2391

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
8 changes: 4 additions & 4 deletions tutorials/asr/10_ASR_CTC_Language_Finetuning.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -39,7 +39,7 @@
"!pip install matplotlib>=3.3.2\n",
"\n",
"## Install NeMo\n",
"BRANCH = \"r1.0.2\"\n",
"BRANCH = \"r1.1.0\"\n",
"!python -m pip install git+https://github.com/NVIDIA/NeMo.git@$BRANCH#egg=nemo_toolkit[all]\n",
"\n",
"\"\"\"\n",
Expand Down Expand Up @@ -899,7 +899,7 @@
"\n",
"------\n",
"\n",
"It is also important to note that if the language remains the same, and some specific domain of text must be targetted for ASR, it is often easier to add a domain-specific language model to guide the generic ASR model than to attempt fine-tuning a full ASR model on limited data from that specific domain. "
"It is also important to note that if the language remains the same, and some specific domain of text must be adapted for ASR, it is often easier to add a domain-specific language model to guide the generic ASR model than to attempt fine-tuning a full ASR model on limited data from that specific domain. "
]
},
{
Expand Down Expand Up @@ -1135,7 +1135,7 @@
"id": "Waz64_NXfkIQ"
},
"source": [
"### Settng up augmentation\n",
"### Setting up augmentation\n",
"\n",
"Remember that the model was trained on several thousands of hours of data, so the regularization provided to it might not suit the current dataset. We can easily change it as we see fit.\n",
"\n",
Expand Down Expand Up @@ -1778,7 +1778,7 @@
"id": "t2iOQlFfs2Ig"
},
"source": [
"### Analyse dataset outliers\n",
"### Examine dataset outliers\n",
"\n",
"In general, there are minor differences between the Character encoding and Sub-word encoding models. Since sub-words can encode larger sequence of tokens into a single subword, they substantially reduce the target sequence length.\n",
"\n",
Expand Down