[Python] How to get fine grained smaller time resolution srt from google cloud speech to text...

I have a working code in python which generates an srt file using google cloud speech to text.

from google.api_core.client_options import ClientOptions
from google.cloud.speech_v2 import SpeechClient
from google.cloud.speech_v2.types import cloud_speech
import json
from google.protobuf.json_format import MessageToDict

MAX_AUDIO_LENGTH_SECS = 8 * 60 * 60


def run_batch_recognize():
# Instantiates a client.
client = SpeechClient(
client_options=ClientOptions(
api_endpoint="us-central1-speech.googleapis.com",
),
)

# The name of the audio file to transcribe:
audio_gcs_uri = "<redacted>"

config = cloud_speech.RecognitionConfig(
explicit_decoding_config=cloud_speech.ExplicitDecodingConfig(
encoding=cloud_speech.ExplicitDecodingConfig.AudioEncoding.LINEAR16,
sample_rate_hertz=24000,
audio_channel_count=1,
),
features=cloud_speech.RecognitionFeatures(
enable_word_confidence=True,
enable_word_time_offsets=True,
enable_automatic_punctuation=True,
max_alternatives=5,
),
# model="chirp_2",
model="short",
language_codes=["en-US"],
)

output_config = cloud_speech.RecognitionOutputConfig(
inline_response_config=cloud_speech.InlineOutputConfig(),
output_format_config=cloud_speech.OutputFormatConfig(
srt=cloud_speech.SrtOutputFileFormatConfig()
),
)

files = [cloud_speech.BatchRecognizeFileMetadata(uri=audio_gcs_uri)]

request = cloud_speech.BatchRecognizeRequest(
recognizer="<redacted>",
config=config,
files=files,
recognition_output_config=output_config,
)
operation = client.batch_recognize(request=request)

print("Waiting for operation to complete...")
response = operation.result(timeout=3 * MAX_AUDIO_LENGTH_SECS)
# print(response)

# Convert the protobuf response to a dictionary using MessageToDict
response_dict = MessageToDict(response._pb)

# Print the response as a formatted JSON string
print(json.dumps(response_dict, indent=2))

# Extract the SRT captions
srt_output = response_dict["results"][audio_gcs_uri]["inlineResult"]["srtCaptions"]

# Print the SRT output
print("SRT Captions:\n")
print(srt_output)


run_batch_recognize()


And it generates a decent srt content like so:

1
00:00:00,040 --> 00:00:02,960
The sun set over the horizon
painting the sky and hues of

2
00:00:02,960 --> 00:00:06,440
orange and pink. A gentle breeze
swept through the trees carrying

3
00:00:06,440 --> 00:00:10,440
the scent of fresh pine. It was
the perfect evening to unwind
and relax.


However is it possible to somehow ask google api to generate srt content such that there is only one or two words at any time? Something like below:

1
00:00:00,040 --> 00:00:00,540
The

2
00:00:00,540 --> 00:00:01,040
sun

3
00:00:01,040 --> 00:00:01,540
set

Continue reading...