From f92830facc78a10f38da6acd0b935814dfdce950 Mon Sep 17 00:00:00 2001 From: Izaya Orihara Date: Mon, 9 Oct 2023 15:17:32 +0200 Subject: [PATCH] Checkout: transfer to different machine --- README.md | 6 ++++-- src/transcriber.py | 2 +- 2 files changed, 5 insertions(+), 3 deletions(-) diff --git a/README.md b/README.md index f48317b..38ef6fb 100644 --- a/README.md +++ b/README.md @@ -16,7 +16,7 @@ pip install -r requirements.txt To generate transcripts create a new job with your specifications (see jobs section below).
-If you need to download the transcriber model (not saved in `data/models`yet) set your huggingface token: +If you need to download the transcriber model (not saved in `data/models` yet) set your huggingface token: On Linux/Mac: @@ -52,11 +52,13 @@ Jobs specify tasks for transcript creation. A job contains the following informa - seperate data production form code - remember to accept the conditions on diarization if you use huggingface - do a config json -- do option to have models already stored and point to them (is this necessary?) +- do option to have models already stored and point to them (is this necessary? > if you do not want to interact with + huggingface yes) - also for single language models - check warnings - downloader for tib-av - more optional setting +- add progress bar ## Structure diff --git a/src/transcriber.py b/src/transcriber.py index 742b4c7..ea28fc4 100644 --- a/src/transcriber.py +++ b/src/transcriber.py @@ -80,7 +80,7 @@ class Transcriber: json.dump(self.transcript_output, f) # Save just the transcripts to a .txt file - transcripts = [seg['value'] for seg in self.transcript_output['segments']] + transcripts = [seg['text'] for seg in self.transcript_output['segments']] with open(output_txt_file, 'w') as f: f.write('\n'.join(transcripts)) except Exception as e: