speechbrain.inference.text module

Specifies the inference interfaces for text-processing modules.

Authors:

• Aku Rouhe 2021

• Peter Plantinga 2021

• Loren Lugosch 2020

• Mirco Ravanelli 2020

• Titouan Parcollet 2021

• Abdel Heba 2021

• Andreas Nautsch 2022, 2023

• Pooneh Mousavi 2023

• Sylvain de Langen 2023

• Adel Moumen 2023

• Pradnya Kandarkar 2023

Summary

Classes:

GPTResponseGenerator	A ready-to-use Response Generator model
GraphemeToPhoneme	A pretrained model implementation for Grapheme-to-Phoneme (G2P) models that take raw natural language text as an input and
Llama2ResponseGenerator	A ready-to-use Response Generator model
ResponseGenerator	A ready-to-use Response Generator model

Reference

class speechbrain.inference.text.GraphemeToPhoneme(*args, **kwargs)

Bases: Pretrained, EncodeDecodePipelineMixin

A pretrained model implementation for Grapheme-to-Phoneme (G2P) models that take raw natural language text as an input and

Example

>>> text = ("English is tough. It can be understood "
...         "through thorough thought though")
>>> from speechbrain.inference.text import GraphemeToPhoneme
>>> tmpdir = getfixture('tmpdir')
>>> g2p = GraphemeToPhoneme.from_hparams('path/to/model', savedir=tmpdir) 
>>> phonemes = g2p.g2p(text) 

INPUT_STATIC_KEYS = ['txt']

OUTPUT_KEYS = ['phonemes']

property phonemes

Returns the available phonemes

property language

Returns the language for which this model is available

g2p(text)

Performs the Grapheme-to-Phoneme conversion

Parameters:

text (str or list[str]) – a single string to be encoded to phonemes - or a sequence of strings

Returns:

result – if a single example was provided, the return value is a single list of phonemes

Return type:

list

load_dependencies()

Loads any relevant model dependencies

__call__(text)

A convenience callable wrapper - same as G2P

Parameters:

text (str or list[str]) – a single string to be encoded to phonemes - or a sequence of strings

Returns:

result – if a single example was provided, the return value is a single list of phonemes

Return type:

list

forward(noisy, lengths=None)

Runs enhancement on the noisy input

training: bool

class speechbrain.inference.text.ResponseGenerator(*args, **kwargs)

Bases: Pretrained

A ready-to-use Response Generator model

The class can be used to generate and continue dialogue given the user input. The given YAML must contain the fields specified in the *_NEEDED[] lists. It needs to be used with custom.py to load the expanded model with added tokens like bos,eos, and speaker’s tokens.

MODULES_NEEDED = ['model']

generate_response(turn)

Complete a dialogue given the user’s input. :param turn: User input which is the last turn of the dialogue. :type turn: str

Returns:

Generated response for the user input based on the dialogue history.

Return type:

response

prepare_input()

Users should modify this function according to their own tasks.

generate()

Users should modify this function according to their own tasks.

training: bool

class speechbrain.inference.text.GPTResponseGenerator(*args, **kwargs)

Bases: ResponseGenerator

A ready-to-use Response Generator model

The class can be used to generate and continue dialogue given the user input. The given YAML must contain the fields specified in the *_NEEDED[] lists. It needs to be used with custom.py to load the expanded GPT model with added tokens like bos,eos, and speaker’s tokens.

Example

>>> from speechbrain.inference.text import GPTResponseGenerator

>>> tmpdir = getfixture("tmpdir")
>>> res_gen_model = GPTResponseGenerator.from_hparams(source="speechbrain/MultiWOZ-GPT-Response_Generation",
... savedir="tmpdir",
... pymodule_file="custom.py")  
>>> response = res_gen_model.generate_response("I want to book a table for dinner")  

generate(inputs)

Complete a dialogue given the user’s input. :param inputs: history_bos which is the tokenized history+input values with appropriate speaker token appended before each turn and history_token_type which determines

the type of each token basd on who is uttered that token (either User or Sytem).

Returns:

Generated hypothesis for the user input based on the dialogue history.

Return type:

response

prepare_input()

Convert user input and previous histories to the format acceptable for GPT model.

It appends all previous history and input and truncates it based on max_history value. It then tokenizes the input and generates additional input that determines the type of each token (Sytem or User).

Returns:

• history_bos – Tokenized history+input values with appropriate speaker token appended before each turn.

• history_token_type – Type of each token basd on who is uttered that token (either User or Sytem)

training: bool

class speechbrain.inference.text.Llama2ResponseGenerator(*args, **kwargs)

Bases: ResponseGenerator

A ready-to-use Response Generator model

The class can be used to generate and continue dialogue given the user input. The given YAML must contain the fields specified in the *_NEEDED[] lists. It needs to be used with custom.py to load the expanded Llama2 model with added tokens like bos,eos, and speaker’s tokens.

Example

>>> from speechbrain.inference.text import Llama2ResponseGenerator

>>> tmpdir = getfixture("tmpdir")
>>> res_gen_model = Llama2ResponseGenerator.from_hparams(source="speechbrain/MultiWOZ-Llama2-Response_Generation",
... savedir="tmpdir",
... pymodule_file="custom.py")  
>>> response = res_gen_model.generate_response("I want to book a table for dinner")  

generate(inputs)

Complete a dialogue given the user’s input. :param inputs: prompted imputs to be passed to llama2 model for generation. :type inputs: prompt_bos

Returns:

Generated hypothesis for the user input based on the dialogue history.

Return type:

response

prepare_input()

Convert user input and previous histories to the format acceptable for Llama2 model.

It appends all previous history and input and truncates it based on max_history value. It then tokenizes the input and add propmts.

Returns:

Tokenized history+input values with appropriate prompt.

Return type:

prompt_bos

training: bool