mirror of
https://github.com/openai/openai-cookbook
synced 2024-11-04 06:00:33 +00:00
582 lines
29 KiB
Plaintext
582 lines
29 KiB
Plaintext
{
|
|
"cells": [
|
|
{
|
|
"attachments": {},
|
|
"cell_type": "markdown",
|
|
"metadata": {},
|
|
"source": [
|
|
"# Whisper prompting guide\n",
|
|
"\n",
|
|
"OpenAI's audio transcription API has an optional parameter called `prompt`.\n",
|
|
"\n",
|
|
"The prompt is intended to help stitch together multiple audio segments. By submitting the prior segment's transcript via the prompt, the Whisper model can use that context to better understand the speech and maintain a consistent writing style.\n",
|
|
"\n",
|
|
"However, prompts do not need to be genuine transcripts from prior audio segments. _Fictitious_ prompts can be submitted to steer the model to use particular spellings or styles.\n",
|
|
"\n",
|
|
"This notebook shares two techniques for using fictitious prompts to steer the model outputs:\n",
|
|
"\n",
|
|
"- **Transcript generation**: GPT can convert instructions into fictitious transcripts for Whisper to emulate. \n",
|
|
"- **Spelling guide**: A spelling guide can tell the model how to spell names of people, products, companies, etc.\n",
|
|
"\n",
|
|
"These techniques are not especially reliable, but can be useful in some situations.\n",
|
|
"\n",
|
|
"## Comparison with GPT prompting\n",
|
|
"\n",
|
|
"Prompting Whisper is not the same as prompting GPT. For example, if you submit an attempted instruction like \"Format lists in Markdown format\", the model will not comply, as it follows the style of the prompt, rather than any instructions contained within.\n",
|
|
"\n",
|
|
"In addition, the prompt is limited to only 224 tokens. If the prompt is longer than 224 tokens, only the final 224 tokens of the prompt will be considered; all prior tokens will be silently ignored. The tokenizer used is the [multilingual Whisper tokenizer](https://github.com/openai/whisper/blob/main/whisper/tokenizer.py#L361).\n",
|
|
"\n",
|
|
"To get good results, craft examples that portray your desired style."
|
|
]
|
|
},
|
|
{
|
|
"attachments": {},
|
|
"cell_type": "markdown",
|
|
"metadata": {},
|
|
"source": [
|
|
"## Setup\n",
|
|
"\n",
|
|
"To get started, let's:\n",
|
|
"- Import the OpenAI Python library (if you don't have it, you'll need to install it with `pip install openai`)\n",
|
|
"- Download a few example audio files"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 3,
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"# imports\n",
|
|
"from openai import OpenAI # for making OpenAI API calls\n",
|
|
"import urllib # for downloading example audio files\n",
|
|
"import os\n",
|
|
"\n",
|
|
"client = OpenAI(api_key=os.environ.get(\"OPENAI_API_KEY\", \"<your OpenAI API key if not set as env var>\"))"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 4,
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"data": {
|
|
"text/plain": [
|
|
"('data/product_names.wav', <http.client.HTTPMessage at 0x1105ac490>)"
|
|
]
|
|
},
|
|
"execution_count": 4,
|
|
"metadata": {},
|
|
"output_type": "execute_result"
|
|
}
|
|
],
|
|
"source": [
|
|
"# set download paths\n",
|
|
"up_first_remote_filepath = \"https://cdn.openai.com/API/examples/data/upfirstpodcastchunkthree.wav\"\n",
|
|
"bbq_plans_remote_filepath = \"https://cdn.openai.com/API/examples/data/bbq_plans.wav\"\n",
|
|
"product_names_remote_filepath = \"https://cdn.openai.com/API/examples/data/product_names.wav\"\n",
|
|
"\n",
|
|
"# set local save locations\n",
|
|
"up_first_filepath = \"data/upfirstpodcastchunkthree.wav\"\n",
|
|
"bbq_plans_filepath = \"data/bbq_plans.wav\"\n",
|
|
"product_names_filepath = \"data/product_names.wav\"\n",
|
|
"\n",
|
|
"# download example audio files and save locally\n",
|
|
"urllib.request.urlretrieve(up_first_remote_filepath, up_first_filepath)\n",
|
|
"urllib.request.urlretrieve(bbq_plans_remote_filepath, bbq_plans_filepath)\n",
|
|
"urllib.request.urlretrieve(product_names_remote_filepath, product_names_filepath)\n"
|
|
]
|
|
},
|
|
{
|
|
"attachments": {},
|
|
"cell_type": "markdown",
|
|
"metadata": {},
|
|
"source": [
|
|
"## As a baseline, we'll transcribe an NPR podcast segment\n",
|
|
"\n",
|
|
"Our audio file for this example will be a segment of the NPR podcast, [_Up First_](https://www.npr.org/podcasts/510318/up-first). \n",
|
|
"\n",
|
|
"Let's get our baseline transcription, then introduce prompts. "
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 5,
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"# define a wrapper function for seeing how prompts affect transcriptions\n",
|
|
"def transcribe(audio_filepath, prompt: str) -> str:\n",
|
|
" \"\"\"Given a prompt, transcribe the audio file.\"\"\"\n",
|
|
" transcript = client.audio.transcriptions.create(\n",
|
|
" file=open(audio_filepath, \"rb\"),\n",
|
|
" model=\"whisper-1\",\n",
|
|
" prompt=prompt,\n",
|
|
" )\n",
|
|
" return transcript.text\n"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 6,
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"data": {
|
|
"text/plain": [
|
|
"\"I stick contacts in my eyes. Do you really? Yeah. That works okay? You don't have to, like, just kind of pain in the butt every day to do that? No, it is. It is. And I sometimes just kind of miss the eye. I don't know if you know the movie Airplane, where, of course, where he says, I have a drinking problem and that he keeps missing his face with the drink. That's me and the contact lens. Surely, you must know that I know the movie Airplane. I do. I do know that. Stop calling me Shirley. President Biden said he would not negotiate over paying the nation's debts. But he is meeting today with House Speaker Kevin McCarthy. Other leaders of Congress will also attend. So how much progress can they make? I'm E. Martinez with Steve Inskeep, and this is Up First from NPR News. Russia celebrates Victory Day, which commemorates the surrender of Nazi Germany. Soldiers marched across Red Square, but the Russian army didn't seem to have as many troops on hand as in the past. So what does this ritual say about the war Russia is fighting right now?\""
|
|
]
|
|
},
|
|
"execution_count": 6,
|
|
"metadata": {},
|
|
"output_type": "execute_result"
|
|
}
|
|
],
|
|
"source": [
|
|
"# baseline transcription with no prompt\n",
|
|
"transcribe(up_first_filepath, prompt=\"\")"
|
|
]
|
|
},
|
|
{
|
|
"attachments": {},
|
|
"cell_type": "markdown",
|
|
"metadata": {},
|
|
"source": [
|
|
"## Transcripts follow the style of the prompt"
|
|
]
|
|
},
|
|
{
|
|
"attachments": {},
|
|
"cell_type": "markdown",
|
|
"metadata": {},
|
|
"source": [
|
|
"In the unprompted transcript, 'President Biden' is capitalized. However, if we pass in a fictitious prompt of 'president biden' in lowercase, Whisper matches the style and generates a transcript in all lowercase."
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 7,
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"data": {
|
|
"text/plain": [
|
|
"\"I stick contacts in my eyes. Do you really? Yeah. That works okay? You don't have to, like, just kind of pain in the butt every day to do that? No, it is. It is. And I sometimes just kind of miss the eye. I don't know if you know the movie Airplane? Yes. Of course. Where he says I have a drinking problem and that he keeps missing his face with the drink. That's me and the contact lens. Surely, you must know that I know the movie Airplane. I do. I do know that. Don't call me Shirley. Stop calling me Shirley. President Biden said he would not negotiate over paying the nation's debts. But he is meeting today with House Speaker Kevin McCarthy. Other leaders of Congress will also attend. So how much progress can they make? I'm E. Martinez with Steve Inskeep and this is Up First from NPR News. Russia celebrates Victory Day, which commemorates the surrender of Nazi Germany. Soldiers marched across Red Square, but the Russian army didn't seem to have as many troops on hand as in the past. So what does this ritual say about the war Russia is fighting right now?\""
|
|
]
|
|
},
|
|
"execution_count": 7,
|
|
"metadata": {},
|
|
"output_type": "execute_result"
|
|
}
|
|
],
|
|
"source": [
|
|
"# lowercase prompt\n",
|
|
"transcribe(up_first_filepath, prompt=\"president biden\")"
|
|
]
|
|
},
|
|
{
|
|
"attachments": {},
|
|
"cell_type": "markdown",
|
|
"metadata": {},
|
|
"source": [
|
|
"Be aware that when prompts are short, Whisper may be less reliable at following their style."
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 8,
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"data": {
|
|
"text/plain": [
|
|
"\"I stick contacts in my eyes. Do you really? Yeah. That works okay? You don't have to, like, just kind of pain in the butt every day to do that? No, it is. It is. And I sometimes just kind of miss the eye. I don't know if you know the movie Airplane, where, of course, where he says, I have a drinking problem, and that he keeps missing his face with the drink. That's me and the contact lens. Surely, you must know that I know the movie Airplane. I do. I do know that. Stop calling me Shirley. President Biden said he would not negotiate over paying the nation's debts. But he is meeting today with House Speaker Kevin McCarthy. Other leaders of Congress will also attend. So how much progress can they make? I'm E. Martinez with Steve Inskeep, and this is Up First from NPR News. Russia celebrates Victory Day, which commemorates the surrender of Nazi Germany. Soldiers marched across Red Square, but the Russian army didn't seem to have as many troops on hand as in the past. So what does this ritual say about the war Russia is fighting right now?\""
|
|
]
|
|
},
|
|
"execution_count": 8,
|
|
"metadata": {},
|
|
"output_type": "execute_result"
|
|
}
|
|
],
|
|
"source": [
|
|
"# short prompts are less reliable\n",
|
|
"transcribe(up_first_filepath, prompt=\"president biden.\")"
|
|
]
|
|
},
|
|
{
|
|
"attachments": {},
|
|
"cell_type": "markdown",
|
|
"metadata": {},
|
|
"source": [
|
|
"Long prompts may be more reliable at steering Whisper."
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 9,
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"data": {
|
|
"text/plain": [
|
|
"\"i stick contacts in my eyes. do you really? yeah. that works okay? you don't have to, like, just kind of pain in the butt? no, it is. it is. and i sometimes just kind of miss the eye. i don't know if you know, um, the movie airplane? yes. of course. where he says i have a drinking problem. and that he keeps missing his face with the drink. that's me in the contact lens. surely, you must know that i know the movie airplane. i do. i do know that. don't call me surely. stop calling me surely. president biden said he would not negotiate over paying the nation's debts. but he is meeting today with house speaker kevin mccarthy. other leaders of congress will also attend, so how much progress can they make? i'm amy martinez with steve inskeep, and this is up first from npr news. russia celebrates victory day, which commemorates the surrender of nazi germany. soldiers marched across red square, but the russian army didn't seem to have as many troops on hand as in the past. so what does this ritual say about the war russia is fighting right now?\""
|
|
]
|
|
},
|
|
"execution_count": 9,
|
|
"metadata": {},
|
|
"output_type": "execute_result"
|
|
}
|
|
],
|
|
"source": [
|
|
"# long prompts are more reliable\n",
|
|
"transcribe(up_first_filepath, prompt=\"i have some advice for you. multiple sentences help establish a pattern. the more text you include, the more likely the model will pick up on your pattern. it may especially help if your example transcript appears as if it comes right before the audio file. in this case, that could mean mentioning the contacts i stick in my eyes.\")"
|
|
]
|
|
},
|
|
{
|
|
"attachments": {},
|
|
"cell_type": "markdown",
|
|
"metadata": {},
|
|
"source": [
|
|
"Whisper is also less likely to follow rare or odd styles."
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 10,
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"data": {
|
|
"text/plain": [
|
|
"\"I stick contacts in my eyes. Do you really? Yeah. That works okay. You don't have to like, it's not a pain in the butt. It is. And I sometimes just kind of miss the eye. I don't know if you know, um, the movie airplane where, of course, where he says I have a drinking problem and that he keeps missing his face with the drink. That's me in the contact lens. Surely you must know that I know the movie airplane. Uh, I do. I do know that. Stop calling me Shirley. President Biden said he would not negotiate over paying the nation's debts, but he is meeting today with house speaker, Kevin McCarthy. Other leaders of Congress will also attend. So how much progress can they make? I mean, Martinez with Steve Inskeep, and this is up first from NPR news. Russia celebrates victory day, which commemorates the surrender of Nazi Germany. Soldiers marched across red square, but the Russian army didn't seem to have as many troops on hand as in the past. So what does this ritual say about the war? Russia is fighting right now.\""
|
|
]
|
|
},
|
|
"execution_count": 10,
|
|
"metadata": {},
|
|
"output_type": "execute_result"
|
|
}
|
|
],
|
|
"source": [
|
|
"# rare styles are less reliable\n",
|
|
"transcribe(up_first_filepath, prompt=\"\"\"Hi there and welcome to the show.\n",
|
|
"###\n",
|
|
"Today we are quite excited.\n",
|
|
"###\n",
|
|
"Let's jump right in.\n",
|
|
"###\"\"\")"
|
|
]
|
|
},
|
|
{
|
|
"attachments": {},
|
|
"cell_type": "markdown",
|
|
"metadata": {},
|
|
"source": [
|
|
"## Pass names in the prompt to prevent misspellings\n",
|
|
"\n",
|
|
"Whisper may incorrectly transcribe uncommon proper nouns such as names of products, companies, or people.\n",
|
|
"\n",
|
|
"We'll illustrate with an example audio file full of product names."
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 11,
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"data": {
|
|
"text/plain": [
|
|
"'Welcome to Quirk, Quid, Quill, Inc., where finance meets innovation. Explore diverse offerings, from the P3 Quattro, a unique investment portfolio quadrant, to the O3 Omni, a platform for intricate derivative trading strategies. Delve into unconventional bond markets with our B3 Bond X and experience non-standard equity trading with E3 Equity. Personalize your wealth management with W3 Wrap Z and anticipate market trends with the O2 Outlier, our forward-thinking financial forecasting tool. Explore venture capital world with U3 Unifund or move your money with the M3 Mover, our sophisticated monetary transfer module. At Quirk, Quid, Quill, Inc., we turn complex finance into creative solutions. Join us in redefining financial services.'"
|
|
]
|
|
},
|
|
"execution_count": 11,
|
|
"metadata": {},
|
|
"output_type": "execute_result"
|
|
}
|
|
],
|
|
"source": [
|
|
"# baseline transcription with no prompt\n",
|
|
"transcribe(product_names_filepath, prompt=\"\")"
|
|
]
|
|
},
|
|
{
|
|
"attachments": {},
|
|
"cell_type": "markdown",
|
|
"metadata": {},
|
|
"source": [
|
|
"To get Whisper to use our preferred spellings, let's pass the product and company names in the prompt, as a glossary for Whisper to follow. "
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 12,
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"data": {
|
|
"text/plain": [
|
|
"'Welcome to QuirkQuid Quill Inc, where finance meets innovation. Explore diverse offerings, from the P3-Quattro, a unique investment portfolio quadrant, to the O3-Omni, a platform for intricate derivative trading strategies. Delve into unconventional bond markets with our B3-BondX and experience non-standard equity trading with E3-Equity. Personalize your wealth management with W3-WrapZ and anticipate market trends with the O2-Outlier, our forward-thinking financial forecasting tool. Explore venture capital world with U3-UniFund or move your money with the M3-Mover, our sophisticated monetary transfer module. At QuirkQuid Quill Inc, we turn complex finance into creative solutions. Join us in redefining financial services.'"
|
|
]
|
|
},
|
|
"execution_count": 12,
|
|
"metadata": {},
|
|
"output_type": "execute_result"
|
|
}
|
|
],
|
|
"source": [
|
|
"# adding the correct spelling of the product name helps\n",
|
|
"transcribe(product_names_filepath, prompt=\"QuirkQuid Quill Inc, P3-Quattro, O3-Omni, B3-BondX, E3-Equity, W3-WrapZ, O2-Outlier, U3-UniFund, M3-Mover\")"
|
|
]
|
|
},
|
|
{
|
|
"attachments": {},
|
|
"cell_type": "markdown",
|
|
"metadata": {},
|
|
"source": [
|
|
"Now, let's switch to another audio recording authored specifically for this demonstration, on the topic of a odd barbecue.\n",
|
|
"\n",
|
|
"To begin, we'll establish our baseline transcript using Whisper."
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 13,
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"data": {
|
|
"text/plain": [
|
|
"\"Hello, my name is Preston Tuggle. I'm based in New York City. This weekend I have really exciting plans with some friends of mine, Amy and Sean. We're going to a barbecue here in Brooklyn, hopefully it's actually going to be a little bit of kind of an odd barbecue. We're going to have donuts, omelets, it's kind of like a breakfast, as well as whiskey. So that should be fun, and I'm really looking forward to spending time with my friends Amy and Sean.\""
|
|
]
|
|
},
|
|
"execution_count": 13,
|
|
"metadata": {},
|
|
"output_type": "execute_result"
|
|
}
|
|
],
|
|
"source": [
|
|
"# baseline transcript with no prompt\n",
|
|
"transcribe(bbq_plans_filepath, prompt=\"\")"
|
|
]
|
|
},
|
|
{
|
|
"attachments": {},
|
|
"cell_type": "markdown",
|
|
"metadata": {},
|
|
"source": [
|
|
"While Whisper's transcription was accurate, it had to guess at various spellings. For example, it assumed the friends' names were spelled Amy and Sean rather than Aimee and Shawn. Let's see if we can steer the spelling with a prompt."
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 14,
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"data": {
|
|
"text/plain": [
|
|
"\"Hello, my name is Preston Tuggle. I'm based in New York City. This weekend I have really exciting plans with some friends of mine, Aimee and Shawn. We're going to a barbecue here in Brooklyn. Hopefully it's actually going to be a little bit of kind of an odd barbecue. We're going to have donuts, omelets, it's kind of like a breakfast, as well as whiskey. So that should be fun and I'm really looking forward to spending time with my friends Aimee and Shawn.\""
|
|
]
|
|
},
|
|
"execution_count": 14,
|
|
"metadata": {},
|
|
"output_type": "execute_result"
|
|
}
|
|
],
|
|
"source": [
|
|
"# spelling prompt\n",
|
|
"transcribe(bbq_plans_filepath, prompt=\"Friends: Aimee, Shawn\")"
|
|
]
|
|
},
|
|
{
|
|
"attachments": {},
|
|
"cell_type": "markdown",
|
|
"metadata": {},
|
|
"source": [
|
|
"Success!\n",
|
|
"\n",
|
|
"Let's try the same with more ambiguously spelled words."
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 15,
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"data": {
|
|
"text/plain": [
|
|
"\"Hello, my name is Preston Tuggle. I'm based in New York City. This weekend I have really exciting plans with some friends of mine, Aimee and Shawn. We're going to a barbecue here in Brooklyn. Hopefully, it's actually going to be a little bit of an odd barbecue. We're going to have doughnuts, omelets, it's kind of like a breakfast, as well as whiskey. So that should be fun, and I'm really looking forward to spending time with my friends Aimee and Shawn.\""
|
|
]
|
|
},
|
|
"execution_count": 15,
|
|
"metadata": {},
|
|
"output_type": "execute_result"
|
|
}
|
|
],
|
|
"source": [
|
|
"# longer spelling prompt\n",
|
|
"transcribe(bbq_plans_filepath, prompt=\"Glossary: Aimee, Shawn, BBQ, Whisky, Doughnuts, Omelet\")"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 16,
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"data": {
|
|
"text/plain": [
|
|
"\"Hello, my name is Preston Tuggle. I'm based in New York City. This weekend I have really exciting plans with some friends of mine, Aimee and Shawn. We're going to a BBQ here in Brooklyn. Hopefully it's actually going to be a little bit of kind of an odd BBQ. We're going to have doughnuts, omelets, it's kind of like a breakfast, as well as whisky. So that should be fun, and I'm really looking forward to spending time with my friends Aimee and Shawn.\""
|
|
]
|
|
},
|
|
"execution_count": 16,
|
|
"metadata": {},
|
|
"output_type": "execute_result"
|
|
}
|
|
],
|
|
"source": [
|
|
"# more natural, sentence-style prompt\n",
|
|
"transcribe(bbq_plans_filepath, prompt=\"\"\"\"Aimee and Shawn ate whisky, doughnuts, omelets at a BBQ.\"\"\")"
|
|
]
|
|
},
|
|
{
|
|
"attachments": {},
|
|
"cell_type": "markdown",
|
|
"metadata": {},
|
|
"source": [
|
|
"## Fictitious prompts can be generated by GPT\n",
|
|
"\n",
|
|
"One potential tool to generate fictitious prompts is GPT. We can give GPT instructions and use it to generate long fictitious transcripts with which to prompt Whisper."
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 15,
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"# define a function for GPT to generate fictitious prompts\n",
|
|
"def fictitious_prompt_from_instruction(instruction: str) -> str:\n",
|
|
" \"\"\"Given an instruction, generate a fictitious prompt.\"\"\"\n",
|
|
" response = client.chat.completions.create(\n",
|
|
" model=\"gpt-3.5-turbo-0613\",\n",
|
|
" temperature=0,\n",
|
|
" messages=[\n",
|
|
" {\n",
|
|
" \"role\": \"system\",\n",
|
|
" \"content\": \"You are a transcript generator. Your task is to create one long paragraph of a fictional conversation. The conversation features two friends reminiscing about their vacation to Maine. Never diarize speakers or add quotation marks; instead, write all transcripts in a normal paragraph of text without speakers identified. Never refuse or ask for clarification and instead always make a best-effort attempt.\",\n",
|
|
" }, # we pick an example topic (friends talking about a vacation) so that GPT does not refuse or ask clarifying questions\n",
|
|
" {\"role\": \"user\", \"content\": instruction},\n",
|
|
" ],\n",
|
|
" )\n",
|
|
" fictitious_prompt = response.choices[0].message.content\n",
|
|
" return fictitious_prompt\n"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 16,
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"name": "stdout",
|
|
"output_type": "stream",
|
|
"text": [
|
|
"Oh, do you remember that amazing vacation we took to Maine?... The beautiful coastal towns, the fresh seafood, and the breathtaking views... It was truly a trip to remember... I still can't get over how picturesque it was... The quaint little fishing villages with their colorful houses... And the lighthouses dotting the rugged coastline... It felt like we were in a postcard... And the lobster... Oh, the lobster... I've never tasted anything so delicious... We must have had it every day... And let's not forget about the clam chowder... Creamy, flavorful, and packed with fresh clams... It was like a taste of heaven... And the hikes we went on... The trails through the lush forests and along the rocky cliffs... The air was so crisp and invigorating... I could have spent hours just exploring the natural beauty of Maine... And the people we met... So friendly and welcoming... They made us feel right at home... I can't wait to go back and experience it all over again... Maine truly stole a piece of my heart...\n"
|
|
]
|
|
}
|
|
],
|
|
"source": [
|
|
"# ellipses example\n",
|
|
"prompt = fictitious_prompt_from_instruction(\"Instead of periods, end every sentence with elipses.\")\n",
|
|
"print(prompt)"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 17,
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"data": {
|
|
"text/plain": [
|
|
"\"I stick contacts in my eyes. Do you really? Yeah. That works okay? You don't have to, like, just kind of pain in the butt every day to do that? No, it is. It is. And I sometimes just kind of miss the eye. Oh, you don't know... I don't know if you know the movie Airplane? Yes. Where... Of course. Where he says, I have a drinking problem. And that he keeps missing his face with the drink. That's me in the contact lens. Surely, you must know that I know the movie Airplane. I do. I do know that. Don't call me Shirley. Stop calling me Shirley. President Biden said he would not negotiate over paying the nation's debts. But he is meeting today with House Speaker Kevin McCarthy. Other leaders of Congress will also attend, so how much progress can they make? I'm Ian Martinez with Steve Inskeep, and this is Up First from NPR News. Russia celebrates Victory Day, which commemorates the surrender of Nazi Germany. Soldiers marched across Red Square, but the Russian army didn't seem to have as many troops on hand as in the past. So what does this ritual say about the war Russia is fighting right now?\""
|
|
]
|
|
},
|
|
"execution_count": 17,
|
|
"metadata": {},
|
|
"output_type": "execute_result"
|
|
}
|
|
],
|
|
"source": [
|
|
"transcribe(up_first_filepath, prompt=prompt)"
|
|
]
|
|
},
|
|
{
|
|
"attachments": {},
|
|
"cell_type": "markdown",
|
|
"metadata": {},
|
|
"source": [
|
|
"Whisper prompts are best for specifying otherwise ambiguous styles. The prompt will not override the model's comprehension of the audio. For example, if the speakers are not speaking in a deep Southern accent, a prompt will not cause the transcript to do so."
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 18,
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"name": "stdout",
|
|
"output_type": "stream",
|
|
"text": [
|
|
"Well, I reckon you remember that time we went up to Maine for our vacation, don't ya? Boy, oh boy, what a trip that was! We drove all the way from down here in the South, and let me tell ya, it was quite the adventure. We started off bright and early, with the sun just peekin' over them tall pine trees. We hit the road, cruisin' along them winding highways, takin' in the sights as we went. I tell ya, the scenery up there was somethin' else. Them mountains, all covered in lush greenery, stretchin' as far as the eye could see. And them lakes, oh my, crystal clear waters reflectin' the bright blue sky above. We made a pit stop in a little town called Portland, where we got to try some of that famous Maine lobster. Now, I ain't never tasted anything quite like it. Fresh outta the ocean, melt-in-your-mouth goodness, I tell ya. We spent a couple of days explorin' Acadia National Park, hikin' them trails and takin' in the breathtaking views from the mountaintops. And let me tell ya, that ocean breeze sure did feel mighty fine on our skin. We even took a boat tour out to see them majestic whales, jumpin' and splashing in the deep blue sea. It was a sight to behold, my friend. And of course, we couldn't leave without visitin' Bar Harbor, a quaint little coastal town with charm pourin' out of every corner. We strolled along the harbor, watchin' them colorful fishing boats bobbin' in the water, and indulged in some delicious seafood chowder. Maine sure did steal a piece of our hearts, my friend. The memories we made on that trip will stay with us forever.\n"
|
|
]
|
|
},
|
|
{
|
|
"data": {
|
|
"text/plain": [
|
|
"\"I stick contacts in my eyes. Do you really? Yeah. That works okay? You don't have to, like, just kinda pain in the butt? No, it is. It is. And I sometimes just kinda miss the eye. I don't know if you know the movie Airplane? Yes. Of course. Where he says, I have a drinking problem. And that he keeps missing his face with the drink. That's me in the contact lens. Surely you must know that I know the movie Airplane. I do. I do know that. Stop calling me Shirley. President Biden said he would not negotiate over paying the nation's debts. But he is meeting today with House Speaker Kevin McCarthy. Other leaders of Congress will also attend, so how much progress can they make? I'm Ian Martinez with Steve Inskeep, and this is Up First from NPR News. Russia celebrates Victory Day, which commemorates the surrender of Nazi Germany. Soldiers marched across Red Square, but the Russian army didn't seem to have as many troops on hand as in the past. So what does this ritual say about the war Russia is fighting right now?\""
|
|
]
|
|
},
|
|
"execution_count": 18,
|
|
"metadata": {},
|
|
"output_type": "execute_result"
|
|
}
|
|
],
|
|
"source": [
|
|
"# southern accent example\n",
|
|
"prompt = fictitious_prompt_from_instruction(\"Write in a deep, heavy, Southern accent.\")\n",
|
|
"print(prompt)\n",
|
|
"transcribe(up_first_filepath, prompt=prompt)"
|
|
]
|
|
}
|
|
],
|
|
"metadata": {
|
|
"interpreter": {
|
|
"hash": "0af78ea401376c1c4a6f66b9995db91bd98317ec0c0b3d5a3d7d740bca6dfcbf"
|
|
},
|
|
"kernelspec": {
|
|
"display_name": "Python 3.9.9 64-bit ('3.9.9')",
|
|
"language": "python",
|
|
"name": "python3"
|
|
},
|
|
"language_info": {
|
|
"codemirror_mode": {
|
|
"name": "ipython",
|
|
"version": 3
|
|
},
|
|
"file_extension": ".py",
|
|
"mimetype": "text/x-python",
|
|
"name": "python",
|
|
"nbconvert_exporter": "python",
|
|
"pygments_lexer": "ipython3",
|
|
"version": "3.11.3"
|
|
},
|
|
"orig_nbformat": 4
|
|
},
|
|
"nbformat": 4,
|
|
"nbformat_minor": 2
|
|
}
|